{
  "schema_version": "powerbi-v2-wide",
  "generated_from_snapshot": "2026-07-26",
  "source_snapshots": {
    "artificial_analysis": "2026-07-26",
    "llmstats": "2026-07-26"
  },
  "artificial_analysis": {
    "models": [
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ai21-labs/jamba-1-7-large:default",
        "family_id": "ai21-labs/jamba-1-7-large",
        "variant_id": "ai21-labs/jamba-1-7-large:default",
        "canonical_name": "Jamba 1.7 Large",
        "source_name": "Jamba 1.7 Large",
        "provider": "AI21 Labs",
        "creator": "AI21 Labs",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "jamba-1-7-large",
        "source_model_url": "https://artificialanalysis.ai/models/jamba-1-7-large",
        "source_rank": 219,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 19,
        "aa_omniscience_index": -56,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 17,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 4,
        "aa_gpqa": 39,
        "aa_scicode": 19,
        "aa_ifbench": 35,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 8,
        "aa_blended_cost_usd_per_1m": 4.4,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 54,
        "aa_speed_p5_tokens_per_second": 30,
        "aa_speed_p25_tokens_per_second": 49,
        "aa_speed_p75_tokens_per_second": 60,
        "aa_speed_p95_tokens_per_second": 62,
        "aa_latency_seconds": 1.4,
        "aa_latency_first_token_seconds": 1.4,
        "aa_latency_p5_seconds": 1.16,
        "aa_latency_p25_seconds": 1.25,
        "aa_latency_p75_seconds": 1.51,
        "aa_latency_p95_seconds": 1.97,
        "aa_total_response_time_seconds": 10.6,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 95.6,
        "llmdex_speed_index": 48.4,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 40.86,
        "llmdex_efficiency_score": 0.56,
        "llmdex_performance_rank": 219,
        "llmdex_value_rank": 167,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ai21-labs/jamba-1-7-mini:default",
        "family_id": "ai21-labs/jamba-1-7-mini",
        "variant_id": "ai21-labs/jamba-1-7-mini:default",
        "canonical_name": "Jamba 1.7 Mini",
        "source_name": "Jamba 1.7 Mini",
        "provider": "AI21 Labs",
        "creator": "AI21 Labs",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "jamba-1-7-mini",
        "source_model_url": "https://artificialanalysis.ai/models/jamba-1-7-mini",
        "source_rank": 240,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 9,
        "aa_omniscience_index": -74,
        "aa_context_window_tokens": 258000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 13,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 4,
        "aa_gpqa": 32,
        "aa_scicode": 9,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 240,
        "llmdex_value_rank": 243,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ai21-labs/jamba-reasoning-3b:reasoning",
        "family_id": "ai21-labs/jamba-reasoning-3b",
        "variant_id": "ai21-labs/jamba-reasoning-3b:reasoning",
        "canonical_name": "Jamba Reasoning 3B",
        "source_name": "Jamba Reasoning 3B",
        "provider": "AI21 Labs",
        "creator": "AI21 Labs",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "jamba-reasoning-3b",
        "source_model_url": "https://artificialanalysis.ai/models/jamba-reasoning-3b",
        "source_rank": 229,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 6,
        "aa_omniscience_index": -74,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 16,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 14,
        "aa_hle": 5,
        "aa_gpqa": 33,
        "aa_scicode": 6,
        "aa_ifbench": 52,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 4,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 229,
        "llmdex_value_rank": 235,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ai9stars/g9v3-3b:default",
        "family_id": "ai9stars/g9v3-3b",
        "variant_id": "ai9stars/g9v3-3b:default",
        "canonical_name": "G9v3-3B",
        "source_name": "G9v3-3B",
        "provider": "AI9Stars",
        "creator": "AI9Stars",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "g9v3-3b",
        "source_model_url": "https://artificialanalysis.ai/models/g9v3-3b",
        "source_rank": 140,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 16,
        "aa_official_coding_index": 12,
        "aa_omniscience_index": -5,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 18,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 6,
        "aa_tau2": null,
        "aa_tau3_banking": 6,
        "aa_lcr": 35,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 88,
        "aa_hle": 4,
        "aa_gpqa": 44,
        "aa_scicode": 18,
        "aa_ifbench": null,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 16,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 47.5,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 140,
        "llmdex_value_rank": 123,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-0-8b:default",
        "family_id": "alibaba/qwen3-5-0-8b",
        "variant_id": "alibaba/qwen3-5-0-8b:default",
        "canonical_name": "Qwen3.5 0.8B",
        "source_name": "Qwen3.5 0.8B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-0-8b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-0-8b",
        "source_rank": 217,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 0,
        "aa_omniscience_index": -35,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 48,
        "aa_tau3_banking": 0,
        "aa_lcr": 5,
        "aa_omniscience_accuracy": 1,
        "aa_non_hallucination_rate": 63,
        "aa_hle": 1,
        "aa_gpqa": 12,
        "aa_scicode": 0,
        "aa_ifbench": 21,
        "aa_critpt": 0,
        "aa_mmmu_pro": 26,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 217,
        "llmdex_value_rank": 229,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-0-8b:non-reasoning",
        "family_id": "alibaba/qwen3-5-0-8b",
        "variant_id": "alibaba/qwen3-5-0-8b:non-reasoning",
        "canonical_name": "Qwen3.5 0.8B (non-reasoning)",
        "source_name": "Qwen3.5 0.8B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-0-8b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-0-8b-non-reasoning",
        "source_rank": 235,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 1.5,
        "aa_omniscience_index": -89,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 65,
        "aa_tau3_banking": 1,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 1,
        "aa_hle": 5,
        "aa_gpqa": 24,
        "aa_scicode": 3,
        "aa_ifbench": 22,
        "aa_critpt": 0,
        "aa_mmmu_pro": 26,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 235,
        "llmdex_value_rank": 247,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-122b-a10b:default",
        "family_id": "alibaba/qwen3-5-122b-a10b",
        "variant_id": "alibaba/qwen3-5-122b-a10b:default",
        "canonical_name": "Qwen3.5 122B A10B",
        "source_name": "Qwen3.5 122B A10B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-122b-a10b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-122b-a10b",
        "source_rank": 71,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 32,
        "aa_official_coding_index": 45,
        "aa_omniscience_index": -40,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 24,
        "aa_terminalbench_hard": 31,
        "aa_terminalbench_v21": 48,
        "aa_tau2": 94,
        "aa_tau3_banking": 14,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 23,
        "aa_gpqa": 86,
        "aa_scicode": 42,
        "aa_ifbench": 76,
        "aa_critpt": 1,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 3.2,
        "aa_blended_cost_usd_per_1m": 1.52,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 133,
        "aa_speed_p5_tokens_per_second": 72,
        "aa_speed_p25_tokens_per_second": 131,
        "aa_speed_p75_tokens_per_second": 142,
        "aa_speed_p95_tokens_per_second": 151,
        "aa_latency_seconds": 2.35,
        "aa_latency_first_token_seconds": 17.4,
        "aa_latency_p5_seconds": 2.28,
        "aa_latency_p25_seconds": 2.32,
        "aa_latency_p75_seconds": 2.53,
        "aa_latency_p95_seconds": 2.62,
        "aa_total_response_time_seconds": 21.16,
        "aa_reasoning_time_seconds": 15.04,
        "llmdex_adjusted_performance": 32,
        "llmdex_cost_index": 98.48,
        "llmdex_speed_index": 51.55,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.85,
        "llmdex_efficiency_score": 52.22,
        "llmdex_performance_rank": 71,
        "llmdex_value_rank": 58,
        "llmdex_efficiency_rank": 30,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-122b-a10b:non-reasoning",
        "family_id": "alibaba/qwen3-5-122b-a10b",
        "variant_id": "alibaba/qwen3-5-122b-a10b:non-reasoning",
        "canonical_name": "Qwen3.5 122B A10B (non-reasoning)",
        "source_name": "Qwen3.5 122B A10B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-122b-a10b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-122b-a10b-non-reasoning",
        "source_rank": 88,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 28,
        "aa_official_coding_index": 41.5,
        "aa_omniscience_index": -54,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 19,
        "aa_terminalbench_hard": 30,
        "aa_terminalbench_v21": 47,
        "aa_tau2": 85,
        "aa_tau3_banking": 9,
        "aa_lcr": 56,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 15,
        "aa_gpqa": 83,
        "aa_scicode": 36,
        "aa_ifbench": 51,
        "aa_critpt": 1,
        "aa_mmmu_pro": 70,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 3.2,
        "aa_blended_cost_usd_per_1m": 1.52,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 145,
        "aa_speed_p5_tokens_per_second": 120,
        "aa_speed_p25_tokens_per_second": 141,
        "aa_speed_p75_tokens_per_second": 154,
        "aa_speed_p95_tokens_per_second": 171,
        "aa_latency_seconds": 2.37,
        "aa_latency_first_token_seconds": 2.37,
        "aa_latency_p5_seconds": 2.27,
        "aa_latency_p25_seconds": 2.3,
        "aa_latency_p75_seconds": 2.55,
        "aa_latency_p95_seconds": 3.85,
        "aa_total_response_time_seconds": 5.83,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 28,
        "llmdex_cost_index": 98.48,
        "llmdex_speed_index": 52.65,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.07,
        "llmdex_efficiency_score": 47.22,
        "llmdex_performance_rank": 88,
        "llmdex_value_rank": 74,
        "llmdex_efficiency_rank": 38,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-2b:default",
        "family_id": "alibaba/qwen3-5-2b",
        "variant_id": "alibaba/qwen3-5-2b:default",
        "canonical_name": "Qwen3.5 2B",
        "source_name": "Qwen3.5 2B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-2b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-2b",
        "source_rank": 206,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 3,
        "aa_omniscience_index": -47,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": 3,
        "aa_tau2": 69,
        "aa_tau3_banking": 2,
        "aa_lcr": 24,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 45,
        "aa_hle": 2,
        "aa_gpqa": 33,
        "aa_scicode": 3,
        "aa_ifbench": 30,
        "aa_critpt": 0,
        "aa_mmmu_pro": 43,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 7,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 206,
        "llmdex_value_rank": 225,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-2b:non-reasoning",
        "family_id": "alibaba/qwen3-5-2b",
        "variant_id": "alibaba/qwen3-5-2b:non-reasoning",
        "canonical_name": "Qwen3.5 2B (non-reasoning)",
        "source_name": "Qwen3.5 2B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-2b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-2b-non-reasoning",
        "source_rank": 216,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 3.5,
        "aa_omniscience_index": -83,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 82,
        "aa_tau3_banking": 2,
        "aa_lcr": 14,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 5,
        "aa_gpqa": 44,
        "aa_scicode": 7,
        "aa_ifbench": 29,
        "aa_critpt": 0,
        "aa_mmmu_pro": 43,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 216,
        "llmdex_value_rank": 230,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-35b-a3b:non-reasoning",
        "family_id": "alibaba/qwen3-5-35b-a3b",
        "variant_id": "alibaba/qwen3-5-35b-a3b:non-reasoning",
        "canonical_name": "Qwen3.5 35B A3B (non-reasoning)",
        "source_name": "Qwen3.5 35B A3B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-35b-a3b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-35b-a3b-non-reasoning",
        "source_rank": 101,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 24,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 15,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": 41,
        "aa_tau2": 86,
        "aa_tau3_banking": 5,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 13,
        "aa_gpqa": 82,
        "aa_scicode": 29,
        "aa_ifbench": 44,
        "aa_critpt": 1,
        "aa_mmmu_pro": 69,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 2,
        "aa_blended_cost_usd_per_1m": 0.95,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 122,
        "aa_speed_p5_tokens_per_second": 105,
        "aa_speed_p25_tokens_per_second": 117,
        "aa_speed_p75_tokens_per_second": 160,
        "aa_speed_p95_tokens_per_second": 189,
        "aa_latency_seconds": 2.18,
        "aa_latency_first_token_seconds": 2.18,
        "aa_latency_p5_seconds": 2.03,
        "aa_latency_p25_seconds": 2.11,
        "aa_latency_p75_seconds": 2.42,
        "aa_latency_p95_seconds": 3.14,
        "aa_total_response_time_seconds": 6.29,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 24,
        "llmdex_cost_index": 99.05,
        "llmdex_speed_index": 51.3,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 51.97,
        "llmdex_efficiency_score": 55.56,
        "llmdex_performance_rank": 101,
        "llmdex_value_rank": 92,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-397b-a17b:default",
        "family_id": "alibaba/qwen3-5-397b-a17b",
        "variant_id": "alibaba/qwen3-5-397b-a17b:default",
        "canonical_name": "Qwen3.5 397B A17B",
        "source_name": "Qwen3.5 397B A17B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-397b-a17b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-397b-a17b",
        "source_rank": 66,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 46.5,
        "aa_omniscience_index": -30,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 23,
        "aa_terminalbench_hard": 41,
        "aa_terminalbench_v21": 51,
        "aa_tau2": 96,
        "aa_tau3_banking": 13,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 31,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 27,
        "aa_gpqa": 89,
        "aa_scicode": 42,
        "aa_ifbench": 79,
        "aa_critpt": 2,
        "aa_mmmu_pro": 77,
        "aa_apex_agents": 15,
        "aa_itbench": 34,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.6,
        "aa_output_cost_usd_per_1m": 3.6,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 68,
        "aa_speed_p5_tokens_per_second": 60,
        "aa_speed_p25_tokens_per_second": 65,
        "aa_speed_p75_tokens_per_second": 71,
        "aa_speed_p95_tokens_per_second": 77,
        "aa_latency_seconds": 2.37,
        "aa_latency_first_token_seconds": 48.89,
        "aa_latency_p5_seconds": 1.88,
        "aa_latency_p25_seconds": 2.17,
        "aa_latency_p75_seconds": 2.62,
        "aa_latency_p95_seconds": 3.27,
        "aa_total_response_time_seconds": 56.19,
        "aa_reasoning_time_seconds": 46.52,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 44.95,
        "llmdex_coverage_score": 93.8,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.45,
        "llmdex_efficiency_score": 48.33,
        "llmdex_performance_rank": 66,
        "llmdex_value_rank": 61,
        "llmdex_efficiency_rank": 37,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-397b-a17b:non-reasoning",
        "family_id": "alibaba/qwen3-5-397b-a17b",
        "variant_id": "alibaba/qwen3-5-397b-a17b:non-reasoning",
        "canonical_name": "Qwen3.5 397B A17B (non-reasoning)",
        "source_name": "Qwen3.5 397B A17B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-397b-a17b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-397b-a17b-non-reasoning",
        "source_rank": 72,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 32,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": null,
        "aa_tau2": 84,
        "aa_tau3_banking": null,
        "aa_lcr": 58,
        "aa_omniscience_accuracy": 24,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 19,
        "aa_gpqa": 86,
        "aa_scicode": 41,
        "aa_ifbench": 52,
        "aa_critpt": 1,
        "aa_mmmu_pro": 53,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.6,
        "aa_output_cost_usd_per_1m": 3.6,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 66,
        "aa_speed_p5_tokens_per_second": 56,
        "aa_speed_p25_tokens_per_second": 60,
        "aa_speed_p75_tokens_per_second": 71,
        "aa_speed_p95_tokens_per_second": 78,
        "aa_latency_seconds": 2.3,
        "aa_latency_first_token_seconds": 2.3,
        "aa_latency_p5_seconds": 1.88,
        "aa_latency_p25_seconds": 2.13,
        "aa_latency_p75_seconds": 2.53,
        "aa_latency_p95_seconds": 3.55,
        "aa_total_response_time_seconds": 9.87,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 32,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 45.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.48,
        "llmdex_efficiency_score": 45.28,
        "llmdex_performance_rank": 72,
        "llmdex_value_rank": 70,
        "llmdex_efficiency_rank": 39,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-4b:default",
        "family_id": "alibaba/qwen3-5-4b",
        "variant_id": "alibaba/qwen3-5-4b:default",
        "canonical_name": "Qwen3.5 4B",
        "source_name": "Qwen3.5 4B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-4b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-4b",
        "source_rank": 118,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 21,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 18,
        "aa_terminalbench_v21": 26,
        "aa_tau2": 92,
        "aa_tau3_banking": 8,
        "aa_lcr": 56,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 8,
        "aa_gpqa": 68,
        "aa_scicode": 16,
        "aa_ifbench": 50,
        "aa_critpt": 0,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.03,
        "aa_output_cost_usd_per_1m": 0.15,
        "aa_blended_cost_usd_per_1m": 0.078,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 41,
        "aa_speed_p5_tokens_per_second": 17,
        "aa_speed_p25_tokens_per_second": 25,
        "aa_speed_p75_tokens_per_second": 57,
        "aa_speed_p95_tokens_per_second": 69,
        "aa_latency_seconds": 0.81,
        "aa_latency_first_token_seconds": 49.17,
        "aa_latency_p5_seconds": 0.55,
        "aa_latency_p25_seconds": 0.65,
        "aa_latency_p75_seconds": 1.12,
        "aa_latency_p95_seconds": 2.16,
        "aa_total_response_time_seconds": 61.26,
        "aa_reasoning_time_seconds": 48.36,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": 99.92,
        "llmdex_speed_index": 50.05,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 49.99,
        "llmdex_efficiency_score": 92.22,
        "llmdex_performance_rank": 118,
        "llmdex_value_rank": 107,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-4b:non-reasoning",
        "family_id": "alibaba/qwen3-5-4b",
        "variant_id": "alibaba/qwen3-5-4b:non-reasoning",
        "canonical_name": "Qwen3.5 4B (non-reasoning)",
        "source_name": "Qwen3.5 4B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-4b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-4b-non-reasoning",
        "source_rank": 141,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 16,
        "aa_official_coding_index": 19.5,
        "aa_omniscience_index": -75,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 88,
        "aa_tau3_banking": 3,
        "aa_lcr": 28,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 7,
        "aa_gpqa": 71,
        "aa_scicode": 18,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": 62,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.03,
        "aa_output_cost_usd_per_1m": 0.15,
        "aa_blended_cost_usd_per_1m": 0.078,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 33,
        "aa_speed_p5_tokens_per_second": 11,
        "aa_speed_p25_tokens_per_second": 24,
        "aa_speed_p75_tokens_per_second": 54,
        "aa_speed_p95_tokens_per_second": 80,
        "aa_latency_seconds": 0.86,
        "aa_latency_first_token_seconds": 0.86,
        "aa_latency_p5_seconds": 0.55,
        "aa_latency_p25_seconds": 0.66,
        "aa_latency_p75_seconds": 1.13,
        "aa_latency_p95_seconds": 1.54,
        "aa_total_response_time_seconds": 15.83,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 16,
        "llmdex_cost_index": 99.92,
        "llmdex_speed_index": 49,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.78,
        "llmdex_efficiency_score": 90.56,
        "llmdex_performance_rank": 141,
        "llmdex_value_rank": 118,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-9b:default",
        "family_id": "alibaba/qwen3-5-9b",
        "variant_id": "alibaba/qwen3-5-9b:default",
        "canonical_name": "Qwen3.5 9B",
        "source_name": "Qwen3.5 9B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-9b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-9b",
        "source_rank": 110,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 21,
        "aa_official_coding_index": 28.5,
        "aa_omniscience_index": -53,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 7,
        "aa_terminalbench_hard": 24,
        "aa_terminalbench_v21": 29,
        "aa_tau2": 87,
        "aa_tau3_banking": 8,
        "aa_lcr": 59,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 13,
        "aa_gpqa": 81,
        "aa_scicode": 28,
        "aa_ifbench": 67,
        "aa_critpt": 0,
        "aa_mmmu_pro": 69,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.164,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 61,
        "aa_speed_p5_tokens_per_second": 25,
        "aa_speed_p25_tokens_per_second": 38,
        "aa_speed_p75_tokens_per_second": 81,
        "aa_speed_p95_tokens_per_second": 112,
        "aa_latency_seconds": 1.83,
        "aa_latency_first_token_seconds": 34.44,
        "aa_latency_p5_seconds": 0.62,
        "aa_latency_p25_seconds": 0.86,
        "aa_latency_p75_seconds": 2.43,
        "aa_latency_p95_seconds": 6.45,
        "aa_total_response_time_seconds": 42.59,
        "aa_reasoning_time_seconds": 32.61,
        "llmdex_adjusted_performance": 21,
        "llmdex_cost_index": 99.84,
        "llmdex_speed_index": 46.95,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 49.84,
        "llmdex_efficiency_score": 84.44,
        "llmdex_performance_rank": 110,
        "llmdex_value_rank": 108,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-9b:non-reasoning",
        "family_id": "alibaba/qwen3-5-9b",
        "variant_id": "alibaba/qwen3-5-9b:non-reasoning",
        "canonical_name": "Qwen3.5 9B (non-reasoning)",
        "source_name": "Qwen3.5 9B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-5-9b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-9b-non-reasoning",
        "source_rank": 115,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 24.5,
        "aa_omniscience_index": -71,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 18,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 85,
        "aa_tau3_banking": 4,
        "aa_lcr": 38,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 1,
        "aa_hle": 9,
        "aa_gpqa": 79,
        "aa_scicode": 28,
        "aa_ifbench": 38,
        "aa_critpt": 1,
        "aa_mmmu_pro": 67,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 20,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 115,
        "llmdex_value_rank": 195,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-omni-flash:default",
        "family_id": "alibaba/qwen3-5-omni-flash",
        "variant_id": "alibaba/qwen3-5-omni-flash:default",
        "canonical_name": "Qwen3.5 Omni Flash",
        "source_name": "Qwen3.5 Omni Flash",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-omni-flash",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-omni-flash",
        "source_rank": 124,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 19,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -66,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": null,
        "aa_tau2": 85,
        "aa_tau3_banking": null,
        "aa_lcr": 44,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 7,
        "aa_gpqa": 74,
        "aa_scicode": 25,
        "aa_ifbench": 38,
        "aa_critpt": 0,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.8,
        "aa_blended_cost_usd_per_1m": 0.38,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 242,
        "aa_speed_p5_tokens_per_second": 203,
        "aa_speed_p25_tokens_per_second": 210,
        "aa_speed_p75_tokens_per_second": 289,
        "aa_speed_p95_tokens_per_second": 304,
        "aa_latency_seconds": 1.84,
        "aa_latency_first_token_seconds": 1.84,
        "aa_latency_p5_seconds": 1.74,
        "aa_latency_p25_seconds": 1.78,
        "aa_latency_p75_seconds": 1.97,
        "aa_latency_p95_seconds": 2.25,
        "aa_total_response_time_seconds": 3.91,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 19,
        "llmdex_cost_index": 99.62,
        "llmdex_speed_index": 65,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.39,
        "llmdex_efficiency_score": 67.78,
        "llmdex_performance_rank": 124,
        "llmdex_value_rank": 87,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-5-omni-plus:default",
        "family_id": "alibaba/qwen3-5-omni-plus",
        "variant_id": "alibaba/qwen3-5-omni-plus:default",
        "canonical_name": "Qwen3.5 Omni Plus",
        "source_name": "Qwen3.5 Omni Plus",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "qwen3-5-omni-plus",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-5-omni-plus",
        "source_rank": 75,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 31,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -12,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 21,
        "aa_terminalbench_v21": null,
        "aa_tau2": 88,
        "aa_tau3_banking": null,
        "aa_lcr": 53,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 64,
        "aa_hle": 14,
        "aa_gpqa": 83,
        "aa_scicode": 41,
        "aa_ifbench": 51,
        "aa_critpt": 1,
        "aa_mmmu_pro": 71,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 4.8,
        "aa_blended_cost_usd_per_1m": 2.16,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 49,
        "aa_speed_p5_tokens_per_second": 39,
        "aa_speed_p25_tokens_per_second": 46,
        "aa_speed_p75_tokens_per_second": 51,
        "aa_speed_p95_tokens_per_second": 60,
        "aa_latency_seconds": 2.39,
        "aa_latency_first_token_seconds": 2.39,
        "aa_latency_p5_seconds": 2.23,
        "aa_latency_p25_seconds": 2.32,
        "aa_latency_p75_seconds": 2.8,
        "aa_latency_p95_seconds": 4.2,
        "aa_total_response_time_seconds": 12.63,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 31,
        "llmdex_cost_index": 97.84,
        "llmdex_speed_index": 42.95,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 53.44,
        "llmdex_efficiency_score": 38.33,
        "llmdex_performance_rank": 75,
        "llmdex_value_rank": 78,
        "llmdex_efficiency_rank": 46,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-6-27b:default",
        "family_id": "alibaba/qwen3-6-27b",
        "variant_id": "alibaba/qwen3-6-27b:default",
        "canonical_name": "Qwen3.6 27B",
        "source_name": "Qwen3.6 27B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-6-27b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-6-27b",
        "source_rank": 54,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 37,
        "aa_official_coding_index": 50.5,
        "aa_omniscience_index": -20,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": 35,
        "aa_terminalbench_v21": 61,
        "aa_tau2": 94,
        "aa_tau3_banking": 15,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 52,
        "aa_hle": 22,
        "aa_gpqa": 84,
        "aa_scicode": 40,
        "aa_ifbench": 68,
        "aa_critpt": 1,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.6,
        "aa_output_cost_usd_per_1m": 3.6,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 56,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 52,
        "aa_speed_p75_tokens_per_second": 61,
        "aa_speed_p95_tokens_per_second": 65,
        "aa_latency_seconds": 3.7,
        "aa_latency_first_token_seconds": 105.25,
        "aa_latency_p5_seconds": 3.55,
        "aa_latency_p25_seconds": 3.63,
        "aa_latency_p75_seconds": 3.87,
        "aa_latency_p95_seconds": 4.06,
        "aa_total_response_time_seconds": 114.19,
        "aa_reasoning_time_seconds": 101.55,
        "llmdex_adjusted_performance": 37,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 37.1,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.38,
        "llmdex_efficiency_score": 50.56,
        "llmdex_performance_rank": 54,
        "llmdex_value_rank": 62,
        "llmdex_efficiency_rank": 33,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-6-27b:non-reasoning",
        "family_id": "alibaba/qwen3-6-27b",
        "variant_id": "alibaba/qwen3-6-27b:non-reasoning",
        "canonical_name": "Qwen3.6 27B (non-reasoning)",
        "source_name": "Qwen3.6 27B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-6-27b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-6-27b-non-reasoning",
        "source_rank": 77,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 30,
        "aa_official_coding_index": 44,
        "aa_omniscience_index": -53,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 30,
        "aa_terminalbench_hard": 21,
        "aa_terminalbench_v21": 51,
        "aa_tau2": 94,
        "aa_tau3_banking": 8,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 14,
        "aa_gpqa": 83,
        "aa_scicode": 37,
        "aa_ifbench": 46,
        "aa_critpt": 1,
        "aa_mmmu_pro": 72,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.6,
        "aa_output_cost_usd_per_1m": 3.6,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 57,
        "aa_speed_p5_tokens_per_second": 48,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 64,
        "aa_speed_p95_tokens_per_second": 68,
        "aa_latency_seconds": 3.73,
        "aa_latency_first_token_seconds": 3.73,
        "aa_latency_p5_seconds": 3.59,
        "aa_latency_p25_seconds": 3.62,
        "aa_latency_p75_seconds": 4,
        "aa_latency_p95_seconds": 4.89,
        "aa_total_response_time_seconds": 12.52,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 30,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 37.05,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 51.87,
        "llmdex_efficiency_score": 43.89,
        "llmdex_performance_rank": 77,
        "llmdex_value_rank": 93,
        "llmdex_efficiency_rank": 41,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-6-35b-a3b:default",
        "family_id": "alibaba/qwen3-6-35b-a3b",
        "variant_id": "alibaba/qwen3-6-35b-a3b:default",
        "canonical_name": "Qwen3.6 35B A3B",
        "source_name": "Qwen3.6 35B A3B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-6-35b-a3b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-6-35b-a3b",
        "source_rank": 73,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 32,
        "aa_official_coding_index": 40.5,
        "aa_omniscience_index": -21,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 28,
        "aa_terminalbench_hard": 35,
        "aa_terminalbench_v21": 45,
        "aa_tau2": 95,
        "aa_tau3_banking": 9,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 50,
        "aa_hle": 20,
        "aa_gpqa": 84,
        "aa_scicode": 36,
        "aa_ifbench": 64,
        "aa_critpt": 0,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 1.49,
        "aa_blended_cost_usd_per_1m": 0.746,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 158,
        "aa_speed_p5_tokens_per_second": 132,
        "aa_speed_p25_tokens_per_second": 140,
        "aa_speed_p75_tokens_per_second": 168,
        "aa_speed_p95_tokens_per_second": 178,
        "aa_latency_seconds": 2.21,
        "aa_latency_first_token_seconds": 36.29,
        "aa_latency_p5_seconds": 2.07,
        "aa_latency_p25_seconds": 2.15,
        "aa_latency_p75_seconds": 2.34,
        "aa_latency_p95_seconds": 2.74,
        "aa_total_response_time_seconds": 39.45,
        "aa_reasoning_time_seconds": 34.07,
        "llmdex_adjusted_performance": 32,
        "llmdex_cost_index": 99.25,
        "llmdex_speed_index": 54.75,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.73,
        "llmdex_efficiency_score": 65,
        "llmdex_performance_rank": 73,
        "llmdex_value_rank": 44,
        "llmdex_efficiency_rank": 22,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-6-35b-a3b:non-reasoning",
        "family_id": "alibaba/qwen3-6-35b-a3b",
        "variant_id": "alibaba/qwen3-6-35b-a3b:non-reasoning",
        "canonical_name": "Qwen3.6 35B A3B (non-reasoning)",
        "source_name": "Qwen3.6 35B A3B (non-reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-6-35b-a3b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-6-35b-a3b-non-reasoning",
        "source_rank": 100,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 24,
        "aa_official_coding_index": 21.5,
        "aa_omniscience_index": -60,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 26,
        "aa_terminalbench_hard": 26,
        "aa_terminalbench_v21": 42,
        "aa_tau2": 85,
        "aa_tau3_banking": 5,
        "aa_lcr": 57,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 7,
        "aa_hle": 13,
        "aa_gpqa": 82,
        "aa_scicode": 1,
        "aa_ifbench": 36,
        "aa_critpt": 0,
        "aa_mmmu_pro": 71,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.38,
        "aa_output_cost_usd_per_1m": 2.25,
        "aa_blended_cost_usd_per_1m": 1.128,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 185,
        "aa_speed_p5_tokens_per_second": 142,
        "aa_speed_p25_tokens_per_second": 162,
        "aa_speed_p75_tokens_per_second": 208,
        "aa_speed_p95_tokens_per_second": 218,
        "aa_latency_seconds": 2.3,
        "aa_latency_first_token_seconds": 2.3,
        "aa_latency_p5_seconds": 2.15,
        "aa_latency_p25_seconds": 2.2,
        "aa_latency_p75_seconds": 2.42,
        "aa_latency_p95_seconds": 3.3,
        "aa_total_response_time_seconds": 5,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 24,
        "llmdex_cost_index": 98.87,
        "llmdex_speed_index": 57,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 53.06,
        "llmdex_efficiency_score": 52.78,
        "llmdex_performance_rank": 100,
        "llmdex_value_rank": 81,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-6-plus:default",
        "family_id": "alibaba/qwen3-6-plus",
        "variant_id": "alibaba/qwen3-6-plus:default",
        "canonical_name": "Qwen3.6 Plus",
        "source_name": "Qwen3.6 Plus",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "qwen3-6-plus",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-6-plus",
        "source_rank": 46,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 40,
        "aa_official_coding_index": 51,
        "aa_omniscience_index": 3,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": 44,
        "aa_terminalbench_v21": 61,
        "aa_tau2": 98,
        "aa_tau3_banking": 16,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 26,
        "aa_non_hallucination_rate": 68,
        "aa_hle": 26,
        "aa_gpqa": 88,
        "aa_scicode": 41,
        "aa_ifbench": 75,
        "aa_critpt": 3,
        "aa_mmmu_pro": 78,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 3,
        "aa_blended_cost_usd_per_1m": 1.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 53,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 50,
        "aa_speed_p75_tokens_per_second": 54,
        "aa_speed_p95_tokens_per_second": 60,
        "aa_latency_seconds": 2.61,
        "aa_latency_first_token_seconds": 107.02,
        "aa_latency_p5_seconds": 2.34,
        "aa_latency_p25_seconds": 2.38,
        "aa_latency_p75_seconds": 3.01,
        "aa_latency_p95_seconds": 3.38,
        "aa_total_response_time_seconds": 116.42,
        "aa_reasoning_time_seconds": 104.41,
        "llmdex_adjusted_performance": 40,
        "llmdex_cost_index": 98.5,
        "llmdex_speed_index": 42.25,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58,
        "llmdex_efficiency_score": 57.78,
        "llmdex_performance_rank": 46,
        "llmdex_value_rank": 29,
        "llmdex_efficiency_rank": 26,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-7-plus:default",
        "family_id": "alibaba/qwen3-7-plus",
        "variant_id": "alibaba/qwen3-7-plus:default",
        "canonical_name": "Qwen3.7 Plus",
        "source_name": "Qwen3.7 Plus",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "qwen3-7-plus",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-7-plus",
        "source_rank": 47,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 39,
        "aa_official_coding_index": 53,
        "aa_omniscience_index": 2,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 22,
        "aa_terminalbench_hard": 47,
        "aa_terminalbench_v21": 61,
        "aa_tau2": 93,
        "aa_tau3_banking": 18,
        "aa_lcr": 65,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 75,
        "aa_hle": 33,
        "aa_gpqa": 90,
        "aa_scicode": 45,
        "aa_ifbench": 78,
        "aa_critpt": 9,
        "aa_mmmu_pro": 80,
        "aa_apex_agents": 22,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 1.6,
        "aa_blended_cost_usd_per_1m": 0.88,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 54,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 50,
        "aa_speed_p75_tokens_per_second": 54,
        "aa_speed_p95_tokens_per_second": 60,
        "aa_latency_seconds": 2.89,
        "aa_latency_first_token_seconds": 40.25,
        "aa_latency_p5_seconds": 2.41,
        "aa_latency_p25_seconds": 2.61,
        "aa_latency_p75_seconds": 3.19,
        "aa_latency_p95_seconds": 3.36,
        "aa_total_response_time_seconds": 49.58,
        "aa_reasoning_time_seconds": 37.35,
        "llmdex_adjusted_performance": 39,
        "llmdex_cost_index": 99.12,
        "llmdex_speed_index": 40.95,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.43,
        "llmdex_efficiency_score": 65.56,
        "llmdex_performance_rank": 47,
        "llmdex_value_rank": 33,
        "llmdex_efficiency_rank": 21,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-7:max",
        "family_id": "alibaba/qwen3-7",
        "variant_id": "alibaba/qwen3-7:max",
        "canonical_name": "Qwen3.7 Max",
        "source_name": "Qwen3.7 Max",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "qwen3-7-max",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-7-max",
        "source_rank": 27,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 46,
        "aa_official_coding_index": 62,
        "aa_omniscience_index": 14,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 39,
        "aa_terminalbench_hard": 51,
        "aa_terminalbench_v21": 75,
        "aa_tau2": 95,
        "aa_tau3_banking": 11,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 30,
        "aa_non_hallucination_rate": 77,
        "aa_hle": 38,
        "aa_gpqa": 92,
        "aa_scicode": 49,
        "aa_ifbench": 81,
        "aa_critpt": 13,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": 42,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 7.5,
        "aa_blended_cost_usd_per_1m": 4.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 197,
        "aa_speed_p5_tokens_per_second": 168,
        "aa_speed_p25_tokens_per_second": 190,
        "aa_speed_p75_tokens_per_second": 205,
        "aa_speed_p95_tokens_per_second": 236,
        "aa_latency_seconds": 2.62,
        "aa_latency_first_token_seconds": 14.83,
        "aa_latency_p5_seconds": 2.35,
        "aa_latency_p25_seconds": 2.38,
        "aa_latency_p75_seconds": 2.76,
        "aa_latency_p95_seconds": 3.89,
        "aa_total_response_time_seconds": 17.36,
        "aa_reasoning_time_seconds": 12.2,
        "llmdex_adjusted_performance": 46,
        "llmdex_cost_index": 95.5,
        "llmdex_speed_index": 56.6,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 62.97,
        "llmdex_efficiency_score": 31.11,
        "llmdex_performance_rank": 27,
        "llmdex_value_rank": 3,
        "llmdex_efficiency_rank": 55,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-coder-next:default",
        "family_id": "alibaba/qwen3-coder-next",
        "variant_id": "alibaba/qwen3-coder-next:default",
        "canonical_name": "Qwen3 Coder Next",
        "source_name": "Qwen3 Coder Next",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-coder-next",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-coder-next",
        "source_rank": 112,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 21,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 11,
        "aa_terminalbench_hard": 18,
        "aa_terminalbench_v21": 38,
        "aa_tau2": 80,
        "aa_tau3_banking": 5,
        "aa_lcr": 40,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 9,
        "aa_gpqa": 74,
        "aa_scicode": 32,
        "aa_ifbench": 35,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.35,
        "aa_output_cost_usd_per_1m": 1.2,
        "aa_blended_cost_usd_per_1m": 0.69,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 123,
        "aa_speed_p5_tokens_per_second": 82,
        "aa_speed_p25_tokens_per_second": 98,
        "aa_speed_p75_tokens_per_second": 161,
        "aa_speed_p95_tokens_per_second": 208,
        "aa_latency_seconds": 1.38,
        "aa_latency_first_token_seconds": 1.38,
        "aa_latency_p5_seconds": 0.93,
        "aa_latency_p25_seconds": 1.02,
        "aa_latency_p75_seconds": 2.92,
        "aa_latency_p95_seconds": 4.92,
        "aa_total_response_time_seconds": 5.43,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 21,
        "llmdex_cost_index": 99.31,
        "llmdex_speed_index": 55.4,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 51.37,
        "llmdex_efficiency_score": 60.56,
        "llmdex_performance_rank": 112,
        "llmdex_value_rank": 96,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-next-80b-a3b:default",
        "family_id": "alibaba/qwen3-next-80b-a3b",
        "variant_id": "alibaba/qwen3-next-80b-a3b:default",
        "canonical_name": "Qwen3 Next 80B A3B",
        "source_name": "Qwen3 Next 80B A3B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-next-80b-a3b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-next-80b-a3b-instruct",
        "source_rank": 155,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 31,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": null,
        "aa_tau2": 22,
        "aa_tau3_banking": null,
        "aa_lcr": 51,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 7,
        "aa_hle": 7,
        "aa_gpqa": 74,
        "aa_scicode": 31,
        "aa_ifbench": 40,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 2,
        "aa_blended_cost_usd_per_1m": 1.1,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 181,
        "aa_speed_p5_tokens_per_second": 140,
        "aa_speed_p25_tokens_per_second": 171,
        "aa_speed_p75_tokens_per_second": 204,
        "aa_speed_p95_tokens_per_second": 220,
        "aa_latency_seconds": 2.27,
        "aa_latency_first_token_seconds": 2.27,
        "aa_latency_p5_seconds": 2.1,
        "aa_latency_p25_seconds": 2.13,
        "aa_latency_p75_seconds": 2.51,
        "aa_latency_p95_seconds": 5.28,
        "aa_total_response_time_seconds": 5.03,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 98.9,
        "llmdex_speed_index": 56.75,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 48.02,
        "llmdex_efficiency_score": 34.44,
        "llmdex_performance_rank": 155,
        "llmdex_value_rank": 116,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-next-80b-a3b:reasoning",
        "family_id": "alibaba/qwen3-next-80b-a3b",
        "variant_id": "alibaba/qwen3-next-80b-a3b:reasoning",
        "canonical_name": "Qwen3 Next 80B A3B (reasoning)",
        "source_name": "Qwen3 Next 80B A3B (reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-next-80b-a3b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-next-80b-a3b-reasoning",
        "source_rank": 137,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 23,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 10,
        "aa_terminalbench_v21": 7,
        "aa_tau2": 42,
        "aa_tau3_banking": 6,
        "aa_lcr": 60,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 12,
        "aa_gpqa": 76,
        "aa_scicode": 39,
        "aa_ifbench": 61,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 2.7,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 191,
        "aa_speed_p5_tokens_per_second": 170,
        "aa_speed_p25_tokens_per_second": 178,
        "aa_speed_p75_tokens_per_second": 206,
        "aa_speed_p95_tokens_per_second": 217,
        "aa_latency_seconds": 2.21,
        "aa_latency_first_token_seconds": 12.69,
        "aa_latency_p5_seconds": 2.04,
        "aa_latency_p25_seconds": 2.11,
        "aa_latency_p75_seconds": 2.3,
        "aa_latency_p95_seconds": 2.63,
        "aa_total_response_time_seconds": 15.3,
        "aa_reasoning_time_seconds": 10.47,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": 97.3,
        "llmdex_speed_index": 58.05,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 49.3,
        "llmdex_efficiency_score": 18.33,
        "llmdex_performance_rank": 137,
        "llmdex_value_rank": 110,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-omni-30b-a3b:default",
        "family_id": "alibaba/qwen3-omni-30b-a3b",
        "variant_id": "alibaba/qwen3-omni-30b-a3b:default",
        "canonical_name": "Qwen3 Omni 30B A3B",
        "source_name": "Qwen3 Omni 30B A3B",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "qwen3-omni-30b-a3b",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-instruct",
        "source_rank": 221,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 19,
        "aa_omniscience_index": -69,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 16,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 2,
        "aa_hle": 5,
        "aa_gpqa": 62,
        "aa_scicode": 19,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": 55,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 0.97,
        "aa_blended_cost_usd_per_1m": 0.538,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 94,
        "aa_speed_p5_tokens_per_second": 82,
        "aa_speed_p25_tokens_per_second": 88,
        "aa_speed_p75_tokens_per_second": 97,
        "aa_speed_p95_tokens_per_second": 99,
        "aa_latency_seconds": 1.89,
        "aa_latency_first_token_seconds": 1.89,
        "aa_latency_p5_seconds": 1.82,
        "aa_latency_p25_seconds": 1.84,
        "aa_latency_p75_seconds": 2.05,
        "aa_latency_p95_seconds": 2.16,
        "aa_total_response_time_seconds": 7.19,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 99.46,
        "llmdex_speed_index": 49.95,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.33,
        "llmdex_efficiency_score": 28.33,
        "llmdex_performance_rank": 221,
        "llmdex_value_rank": 156,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "alibaba/qwen3-omni-30b-a3b:reasoning",
        "family_id": "alibaba/qwen3-omni-30b-a3b",
        "variant_id": "alibaba/qwen3-omni-30b-a3b:reasoning",
        "canonical_name": "Qwen3 Omni 30B A3B (reasoning)",
        "source_name": "Qwen3 Omni 30B A3B (reasoning)",
        "provider": "Alibaba",
        "creator": "Alibaba",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "qwen3-omni-30b-a3b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/qwen3-omni-30b-a3b-reasoning",
        "source_rank": 178,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 10,
        "aa_official_coding_index": 31,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 21,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 7,
        "aa_gpqa": 73,
        "aa_scicode": 31,
        "aa_ifbench": 43,
        "aa_critpt": 0,
        "aa_mmmu_pro": 60,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 0.97,
        "aa_blended_cost_usd_per_1m": 0.538,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 95,
        "aa_speed_p5_tokens_per_second": 84,
        "aa_speed_p25_tokens_per_second": 90,
        "aa_speed_p75_tokens_per_second": 102,
        "aa_speed_p95_tokens_per_second": 106,
        "aa_latency_seconds": 1.94,
        "aa_latency_first_token_seconds": 23.09,
        "aa_latency_p5_seconds": 1.85,
        "aa_latency_p25_seconds": 1.89,
        "aa_latency_p75_seconds": 2.1,
        "aa_latency_p95_seconds": 2.41,
        "aa_total_response_time_seconds": 28.37,
        "aa_reasoning_time_seconds": 21.15,
        "llmdex_adjusted_performance": 10,
        "llmdex_cost_index": 99.46,
        "llmdex_speed_index": 49.8,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 44.8,
        "llmdex_efficiency_score": 47.78,
        "llmdex_performance_rank": 178,
        "llmdex_value_rank": 141,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/molmo-7b-d:default",
        "family_id": "allen-institute-for-ai/molmo-7b-d",
        "variant_id": "allen-institute-for-ai/molmo-7b-d:default",
        "canonical_name": "Molmo 7B-D",
        "source_name": "Molmo 7B-D",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "molmo-7b-d",
        "source_model_url": "https://artificialanalysis.ai/models/molmo-7b-d",
        "source_rank": 232,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 4100,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 5,
        "aa_gpqa": 24,
        "aa_scicode": 4,
        "aa_ifbench": 20,
        "aa_critpt": null,
        "aa_mmmu_pro": 25,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 34.4,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 4,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 232,
        "llmdex_value_rank": 238,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/molmo2-8b:default",
        "family_id": "allen-institute-for-ai/molmo2-8b",
        "variant_id": "allen-institute-for-ai/molmo2-8b:default",
        "canonical_name": "Molmo2-8B",
        "source_name": "Molmo2-8B",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "molmo2-8b",
        "source_model_url": "https://artificialanalysis.ai/models/molmo2-8b",
        "source_rank": 249,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 13,
        "aa_omniscience_index": -69,
        "aa_context_window_tokens": 36900,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 4,
        "aa_gpqa": 43,
        "aa_scicode": 13,
        "aa_ifbench": 27,
        "aa_critpt": 0,
        "aa_mmmu_pro": 37,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 249,
        "llmdex_value_rank": 253,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/olmo-3-1-32b-instruct:default",
        "family_id": "allen-institute-for-ai/olmo-3-1-32b-instruct",
        "variant_id": "allen-institute-for-ai/olmo-3-1-32b-instruct:default",
        "canonical_name": "Olmo 3.1 32B Instruct",
        "source_name": "Olmo 3.1 32B Instruct",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "olmo-3-1-32b-instruct",
        "source_model_url": "https://artificialanalysis.ai/models/olmo-3-1-32b-instruct",
        "source_rank": 209,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 17,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 21,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 30,
        "aa_hle": 5,
        "aa_gpqa": 54,
        "aa_scicode": 17,
        "aa_ifbench": 39,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 209,
        "llmdex_value_rank": 228,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/olmo-3-1-32b-think:default",
        "family_id": "allen-institute-for-ai/olmo-3-1-32b-think",
        "variant_id": "allen-institute-for-ai/olmo-3-1-32b-think:default",
        "canonical_name": "Olmo 3.1 32B Think",
        "source_name": "Olmo 3.1 32B Think",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "olmo-3-1-32b-think",
        "source_model_url": "https://artificialanalysis.ai/models/olmo-3-1-32b-think",
        "source_rank": 199,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 8,
        "aa_official_coding_index": 29,
        "aa_omniscience_index": -44,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 33,
        "aa_hle": 6,
        "aa_gpqa": 59,
        "aa_scicode": 29,
        "aa_ifbench": 66,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 8,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 42.5,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 199,
        "llmdex_value_rank": 152,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/olmo-3-7b-think:default",
        "family_id": "allen-institute-for-ai/olmo-3-7b-think",
        "variant_id": "allen-institute-for-ai/olmo-3-7b-think:default",
        "canonical_name": "Olmo 3 7B Think",
        "source_name": "Olmo 3 7B Think",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "olmo-3-7b-think",
        "source_model_url": "https://artificialanalysis.ai/models/olmo-3-7b-think",
        "source_rank": 231,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 21,
        "aa_omniscience_index": -74,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 6,
        "aa_gpqa": 52,
        "aa_scicode": 21,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 4,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 231,
        "llmdex_value_rank": 239,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "allen-institute-for-ai/olmo-3-7b:default",
        "family_id": "allen-institute-for-ai/olmo-3-7b",
        "variant_id": "allen-institute-for-ai/olmo-3-7b:default",
        "canonical_name": "Olmo 3 7B",
        "source_name": "Olmo 3 7B",
        "provider": "Allen Institute for AI",
        "creator": "Allen Institute for AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "olmo-3-7b",
        "source_model_url": "https://artificialanalysis.ai/models/olmo-3-7b-instruct",
        "source_rank": 237,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 10,
        "aa_omniscience_index": -78,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 6,
        "aa_gpqa": 40,
        "aa_scicode": 10,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.14,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": 99.86,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 39.32,
        "llmdex_efficiency_score": 53.33,
        "llmdex_performance_rank": 237,
        "llmdex_value_rank": 174,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-lite:default",
        "family_id": "amazon/nova-2-0-lite",
        "variant_id": "amazon/nova-2-0-lite:default",
        "canonical_name": "Nova 2.0 Lite",
        "source_name": "Nova 2.0 Lite",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-lite",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-lite",
        "source_rank": 168,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": null,
        "aa_tau2": 62,
        "aa_tau3_banking": null,
        "aa_lcr": 18,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 3,
        "aa_gpqa": 60,
        "aa_scicode": 24,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": 49,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 148,
        "aa_speed_p5_tokens_per_second": 104,
        "aa_speed_p25_tokens_per_second": 125,
        "aa_speed_p75_tokens_per_second": 185,
        "aa_speed_p95_tokens_per_second": 237,
        "aa_latency_seconds": 1.1,
        "aa_latency_first_token_seconds": 1.1,
        "aa_latency_p5_seconds": 1.01,
        "aa_latency_p25_seconds": 1.04,
        "aa_latency_p75_seconds": 1.18,
        "aa_latency_p95_seconds": 2.13,
        "aa_total_response_time_seconds": 4.47,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 59.3,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.51,
        "llmdex_efficiency_score": 30,
        "llmdex_performance_rank": 168,
        "llmdex_value_rank": 122,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-lite:high-reasoning",
        "family_id": "amazon/nova-2-0-lite",
        "variant_id": "amazon/nova-2-0-lite:high-reasoning",
        "canonical_name": "Nova 2.0 Lite (high) (reasoning)",
        "source_name": "Nova 2.0 Lite (high) (reasoning)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-lite-high-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-lite-reasoning",
        "source_rank": 126,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 26.5,
        "aa_omniscience_index": -54,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 5,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": 16,
        "aa_tau2": 73,
        "aa_tau3_banking": 7,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 11,
        "aa_gpqa": 81,
        "aa_scicode": 37,
        "aa_ifbench": 71,
        "aa_critpt": 0,
        "aa_mmmu_pro": 64,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 160,
        "aa_speed_p5_tokens_per_second": 79,
        "aa_speed_p25_tokens_per_second": 132,
        "aa_speed_p75_tokens_per_second": 188,
        "aa_speed_p95_tokens_per_second": 250,
        "aa_latency_seconds": 18.92,
        "aa_latency_first_token_seconds": 31.39,
        "aa_latency_p5_seconds": 5.44,
        "aa_latency_p25_seconds": 11.18,
        "aa_latency_p75_seconds": 24.98,
        "aa_latency_p95_seconds": 39.87,
        "aa_total_response_time_seconds": 34.51,
        "aa_reasoning_time_seconds": 12.48,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 16,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 41.85,
        "llmdex_efficiency_score": 40.83,
        "llmdex_performance_rank": 126,
        "llmdex_value_rank": 162,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-lite:low",
        "family_id": "amazon/nova-2-0-lite",
        "variant_id": "amazon/nova-2-0-lite:low",
        "canonical_name": "Nova 2.0 Lite (low)",
        "source_name": "Nova 2.0 Lite (low)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-lite-low",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-low",
        "source_rank": 129,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 33,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 72,
        "aa_tau3_banking": null,
        "aa_lcr": 52,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 4,
        "aa_gpqa": 70,
        "aa_scicode": 33,
        "aa_ifbench": 61,
        "aa_critpt": 0,
        "aa_mmmu_pro": 58,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 152,
        "aa_speed_p5_tokens_per_second": 117,
        "aa_speed_p25_tokens_per_second": 139,
        "aa_speed_p75_tokens_per_second": 189,
        "aa_speed_p95_tokens_per_second": 223,
        "aa_latency_seconds": 9.83,
        "aa_latency_first_token_seconds": 23.02,
        "aa_latency_p5_seconds": 4.56,
        "aa_latency_p25_seconds": 7.07,
        "aa_latency_p75_seconds": 12.81,
        "aa_latency_p95_seconds": 19.97,
        "aa_total_response_time_seconds": 26.32,
        "aa_reasoning_time_seconds": 13.19,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 16.05,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 41.86,
        "llmdex_efficiency_score": 40.83,
        "llmdex_performance_rank": 129,
        "llmdex_value_rank": 161,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-lite:medium",
        "family_id": "amazon/nova-2-0-lite",
        "variant_id": "amazon/nova-2-0-lite:medium",
        "canonical_name": "Nova 2.0 Lite (medium)",
        "source_name": "Nova 2.0 Lite (medium)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "nova-2-0-lite-medium",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-lite-reasoning-medium",
        "source_rank": 123,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 19,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -56,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": null,
        "aa_tau2": 76,
        "aa_tau3_banking": null,
        "aa_lcr": 58,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 9,
        "aa_gpqa": 77,
        "aa_scicode": 37,
        "aa_ifbench": 69,
        "aa_critpt": 0,
        "aa_mmmu_pro": 63,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 153,
        "aa_speed_p5_tokens_per_second": 83,
        "aa_speed_p25_tokens_per_second": 120,
        "aa_speed_p75_tokens_per_second": 190,
        "aa_speed_p95_tokens_per_second": 238,
        "aa_latency_seconds": 19.37,
        "aa_latency_first_token_seconds": 32.47,
        "aa_latency_p5_seconds": 7.6,
        "aa_latency_p25_seconds": 14.95,
        "aa_latency_p75_seconds": 23.79,
        "aa_latency_p95_seconds": 31.56,
        "aa_total_response_time_seconds": 35.75,
        "aa_reasoning_time_seconds": 13.11,
        "llmdex_adjusted_performance": 19,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 15.3,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.21,
        "llmdex_efficiency_score": 42.22,
        "llmdex_performance_rank": 123,
        "llmdex_value_rank": 158,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-omni:default",
        "family_id": "amazon/nova-2-0-omni",
        "variant_id": "amazon/nova-2-0-omni:default",
        "canonical_name": "Nova 2.0 Omni",
        "source_name": "Nova 2.0 Omni",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-omni",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-omni",
        "source_rank": 174,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 11,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -65,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": null,
        "aa_tau2": 45,
        "aa_tau3_banking": null,
        "aa_lcr": 22,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 4,
        "aa_gpqa": 55,
        "aa_scicode": 28,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": 50,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 11,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 43.93,
        "llmdex_efficiency_score": 28.89,
        "llmdex_performance_rank": 174,
        "llmdex_value_rank": 146,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-omni:low",
        "family_id": "amazon/nova-2-0-omni",
        "variant_id": "amazon/nova-2-0-omni:low",
        "canonical_name": "Nova 2.0 Omni (low)",
        "source_name": "Nova 2.0 Omni (low)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-omni-low",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-omni-reasoning-low",
        "source_rank": 138,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 34,
        "aa_omniscience_index": -50,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 68,
        "aa_tau3_banking": null,
        "aa_lcr": 51,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 4,
        "aa_gpqa": 70,
        "aa_scicode": 34,
        "aa_ifbench": 62,
        "aa_critpt": 0,
        "aa_mmmu_pro": 60,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 47.68,
        "llmdex_efficiency_score": 38.89,
        "llmdex_performance_rank": 138,
        "llmdex_value_rank": 119,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-omni:medium",
        "family_id": "amazon/nova-2-0-omni",
        "variant_id": "amazon/nova-2-0-omni:medium",
        "canonical_name": "Nova 2.0 Omni (medium)",
        "source_name": "Nova 2.0 Omni (medium)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "nova-2-0-omni-medium",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-omni-reasoning-medium",
        "source_rank": 113,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 21,
        "aa_official_coding_index": 36,
        "aa_omniscience_index": -58,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 80,
        "aa_tau3_banking": null,
        "aa_lcr": 54,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 7,
        "aa_gpqa": 76,
        "aa_scicode": 36,
        "aa_ifbench": 66,
        "aa_critpt": 0,
        "aa_mmmu_pro": 62,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 21,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 50.18,
        "llmdex_efficiency_score": 46.11,
        "llmdex_performance_rank": 113,
        "llmdex_value_rank": 103,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-pro-preview:low-preview",
        "family_id": "amazon/nova-2-0-pro-preview",
        "variant_id": "amazon/nova-2-0-pro-preview:low-preview",
        "canonical_name": "Nova 2.0 Pro Preview (low)",
        "source_name": "Nova 2.0 Pro Preview (low)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-pro-preview-low",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-low",
        "source_rank": 120,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 29,
        "aa_omniscience_index": -46,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 8,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": 19,
        "aa_tau2": 91,
        "aa_tau3_banking": 9,
        "aa_lcr": 62,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 5,
        "aa_gpqa": 75,
        "aa_scicode": 39,
        "aa_ifbench": 80,
        "aa_critpt": 0,
        "aa_mmmu_pro": 63,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 4.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 116,
        "aa_speed_p5_tokens_per_second": 103,
        "aa_speed_p25_tokens_per_second": 110,
        "aa_speed_p75_tokens_per_second": 144,
        "aa_speed_p95_tokens_per_second": 161,
        "aa_latency_seconds": 11.99,
        "aa_latency_first_token_seconds": 29.25,
        "aa_latency_p5_seconds": 6.96,
        "aa_latency_p25_seconds": 9.73,
        "aa_latency_p75_seconds": 15.02,
        "aa_latency_p95_seconds": 24.56,
        "aa_total_response_time_seconds": 33.56,
        "aa_reasoning_time_seconds": 17.25,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": 95.25,
        "llmdex_speed_index": 11.6,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 40.9,
        "llmdex_efficiency_score": 10,
        "llmdex_performance_rank": 120,
        "llmdex_value_rank": 166,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-pro-preview:medium-preview",
        "family_id": "amazon/nova-2-0-pro-preview",
        "variant_id": "amazon/nova-2-0-pro-preview:medium-preview",
        "canonical_name": "Nova 2.0 Pro Preview (medium)",
        "source_name": "Nova 2.0 Pro Preview (medium)",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "nova-2-0-pro-preview-medium",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-pro-reasoning-medium",
        "source_rank": 109,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 22,
        "aa_official_coding_index": 36.5,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 9,
        "aa_terminalbench_hard": 24,
        "aa_terminalbench_v21": 30,
        "aa_tau2": 93,
        "aa_tau3_banking": 8,
        "aa_lcr": 54,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 9,
        "aa_gpqa": 78,
        "aa_scicode": 43,
        "aa_ifbench": 79,
        "aa_critpt": 0,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 4.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 115,
        "aa_speed_p5_tokens_per_second": 103,
        "aa_speed_p25_tokens_per_second": 108,
        "aa_speed_p75_tokens_per_second": 141,
        "aa_speed_p95_tokens_per_second": 166,
        "aa_latency_seconds": 15.13,
        "aa_latency_first_token_seconds": 32.46,
        "aa_latency_p5_seconds": 5.23,
        "aa_latency_p25_seconds": 11.74,
        "aa_latency_p75_seconds": 18.82,
        "aa_latency_p95_seconds": 24.11,
        "aa_total_response_time_seconds": 36.79,
        "aa_reasoning_time_seconds": 17.33,
        "llmdex_adjusted_performance": 22,
        "llmdex_cost_index": 95.25,
        "llmdex_speed_index": 11.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 41.88,
        "llmdex_efficiency_score": 13.89,
        "llmdex_performance_rank": 109,
        "llmdex_value_rank": 160,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-2-0-pro-preview:preview",
        "family_id": "amazon/nova-2-0-pro-preview",
        "variant_id": "amazon/nova-2-0-pro-preview:preview",
        "canonical_name": "Nova 2.0 Pro Preview",
        "source_name": "Nova 2.0 Pro Preview",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "nova-2-0-pro-preview",
        "source_model_url": "https://artificialanalysis.ai/models/nova-2-0-pro",
        "source_rank": 148,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 22.5,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 3,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": 17,
        "aa_tau2": 72,
        "aa_tau3_banking": 7,
        "aa_lcr": 28,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 23,
        "aa_hle": 4,
        "aa_gpqa": 64,
        "aa_scicode": 28,
        "aa_ifbench": 52,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 4.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 103,
        "aa_speed_p5_tokens_per_second": 87,
        "aa_speed_p25_tokens_per_second": 93,
        "aa_speed_p75_tokens_per_second": 121,
        "aa_speed_p95_tokens_per_second": 148,
        "aa_latency_seconds": 0.97,
        "aa_latency_first_token_seconds": 0.97,
        "aa_latency_p5_seconds": 0.89,
        "aa_latency_p25_seconds": 0.94,
        "aa_latency_p75_seconds": 1.08,
        "aa_latency_p95_seconds": 1.38,
        "aa_total_response_time_seconds": 5.85,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 95.25,
        "llmdex_speed_index": 55.45,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.67,
        "llmdex_efficiency_score": 5.56,
        "llmdex_performance_rank": 148,
        "llmdex_value_rank": 128,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-micro:default",
        "family_id": "amazon/nova-micro",
        "variant_id": "amazon/nova-micro:default",
        "canonical_name": "Nova Micro",
        "source_name": "Nova Micro",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "nova-micro",
        "source_model_url": "https://artificialanalysis.ai/models/nova-micro",
        "source_rank": 224,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 9,
        "aa_omniscience_index": -49,
        "aa_context_window_tokens": 130000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 14,
        "aa_tau3_banking": null,
        "aa_lcr": 10,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 35,
        "aa_hle": 5,
        "aa_gpqa": 36,
        "aa_scicode": 9,
        "aa_ifbench": 29,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.04,
        "aa_output_cost_usd_per_1m": 0.14,
        "aa_blended_cost_usd_per_1m": 0.08,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 298,
        "aa_speed_p5_tokens_per_second": 238,
        "aa_speed_p25_tokens_per_second": 258,
        "aa_speed_p75_tokens_per_second": 341,
        "aa_speed_p95_tokens_per_second": 400,
        "aa_latency_seconds": 0.9,
        "aa_latency_first_token_seconds": 0.9,
        "aa_latency_p5_seconds": 0.82,
        "aa_latency_p25_seconds": 0.85,
        "aa_latency_p75_seconds": 1.13,
        "aa_latency_p95_seconds": 2.21,
        "aa_total_response_time_seconds": 2.58,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 99.92,
        "llmdex_speed_index": 75.3,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.54,
        "llmdex_efficiency_score": 73.33,
        "llmdex_performance_rank": 224,
        "llmdex_value_rank": 121,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "amazon/nova-premier:default",
        "family_id": "amazon/nova-premier",
        "variant_id": "amazon/nova-premier:default",
        "canonical_name": "Nova Premier",
        "source_name": "Nova Premier",
        "provider": "Amazon",
        "creator": "Amazon",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "nova-premier",
        "source_model_url": "https://artificialanalysis.ai/models/nova-premier",
        "source_rank": 160,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 13,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": null,
        "aa_tau2": 38,
        "aa_tau3_banking": null,
        "aa_lcr": 30,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 32,
        "aa_hle": 5,
        "aa_gpqa": 57,
        "aa_scicode": 28,
        "aa_ifbench": 36,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 12.5,
        "aa_blended_cost_usd_per_1m": 6.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 32,
        "aa_speed_p5_tokens_per_second": 24,
        "aa_speed_p25_tokens_per_second": 30,
        "aa_speed_p75_tokens_per_second": 35,
        "aa_speed_p95_tokens_per_second": 37,
        "aa_latency_seconds": 2.88,
        "aa_latency_first_token_seconds": 2.88,
        "aa_latency_p5_seconds": 2.78,
        "aa_latency_p25_seconds": 2.83,
        "aa_latency_p75_seconds": 2.98,
        "aa_latency_p95_seconds": 3.48,
        "aa_total_response_time_seconds": 18.39,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 13,
        "llmdex_cost_index": 93.5,
        "llmdex_speed_index": 38.8,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.31,
        "llmdex_efficiency_score": 3.33,
        "llmdex_performance_rank": 160,
        "llmdex_value_rank": 157,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-4-5-haiku:default",
        "family_id": "anthropic/claude-4-5-haiku",
        "variant_id": "anthropic/claude-4-5-haiku:default",
        "canonical_name": "Claude 4.5 Haiku",
        "source_name": "Claude 4.5 Haiku",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-4-5-haiku",
        "source_model_url": "https://artificialanalysis.ai/models/claude-4-5-haiku",
        "source_rank": 103,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 24,
        "aa_official_coding_index": 34,
        "aa_omniscience_index": -8,
        "aa_context_window_tokens": 200000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": null,
        "aa_tau2": 32,
        "aa_tau3_banking": null,
        "aa_lcr": 44,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 75,
        "aa_hle": 4,
        "aa_gpqa": 65,
        "aa_scicode": 34,
        "aa_ifbench": 42,
        "aa_critpt": 0,
        "aa_mmmu_pro": 55,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 5,
        "aa_blended_cost_usd_per_1m": 2.6,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 90,
        "aa_speed_p5_tokens_per_second": 76,
        "aa_speed_p25_tokens_per_second": 81,
        "aa_speed_p75_tokens_per_second": 104,
        "aa_speed_p95_tokens_per_second": 206,
        "aa_latency_seconds": 0.84,
        "aa_latency_first_token_seconds": 0.84,
        "aa_latency_p5_seconds": 0.7,
        "aa_latency_p25_seconds": 0.75,
        "aa_latency_p75_seconds": 1.02,
        "aa_latency_p95_seconds": 1.96,
        "aa_total_response_time_seconds": 6.39,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 24,
        "llmdex_cost_index": 97.4,
        "llmdex_speed_index": 54.8,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.18,
        "llmdex_efficiency_score": 27.78,
        "llmdex_performance_rank": 103,
        "llmdex_value_rank": 89,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-4-5-haiku:reasoning",
        "family_id": "anthropic/claude-4-5-haiku",
        "variant_id": "anthropic/claude-4-5-haiku:reasoning",
        "canonical_name": "Claude 4.5 Haiku (reasoning)",
        "source_name": "Claude 4.5 Haiku (reasoning)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-4-5-haiku-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/claude-4-5-haiku-reasoning",
        "source_rank": 81,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 30,
        "aa_official_coding_index": 43.5,
        "aa_omniscience_index": -4,
        "aa_context_window_tokens": 200000,
        "aa_gdpval": 21,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": 44,
        "aa_tau2": 55,
        "aa_tau3_banking": 9,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 74,
        "aa_hle": 10,
        "aa_gpqa": 67,
        "aa_scicode": 43,
        "aa_ifbench": 54,
        "aa_critpt": 0,
        "aa_mmmu_pro": 59,
        "aa_apex_agents": null,
        "aa_itbench": 27,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 5,
        "aa_blended_cost_usd_per_1m": 2.6,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 92,
        "aa_speed_p5_tokens_per_second": 73,
        "aa_speed_p25_tokens_per_second": 84,
        "aa_speed_p75_tokens_per_second": 144,
        "aa_speed_p95_tokens_per_second": 206,
        "aa_latency_seconds": 11.93,
        "aa_latency_first_token_seconds": 11.93,
        "aa_latency_p5_seconds": 4.82,
        "aa_latency_p25_seconds": 9.83,
        "aa_latency_p75_seconds": 18.49,
        "aa_latency_p95_seconds": 98.95,
        "aa_total_response_time_seconds": 17.35,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 30,
        "llmdex_cost_index": 97.4,
        "llmdex_speed_index": 9.2,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.06,
        "llmdex_efficiency_score": 32.78,
        "llmdex_performance_rank": 81,
        "llmdex_value_rank": 132,
        "llmdex_efficiency_rank": 52,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-fable-5:fallback",
        "family_id": "anthropic/claude-fable-5",
        "variant_id": "anthropic/claude-fable-5:fallback",
        "canonical_name": "Claude Fable 5 (with fallback)",
        "source_name": "Claude Fable 5 (with fallback)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-fable-5-with-fallback",
        "source_model_url": "https://artificialanalysis.ai/models/claude-fable-5",
        "source_rank": 3,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 60,
        "aa_official_coding_index": 72.5,
        "aa_omniscience_index": 40,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 62,
        "aa_terminalbench_hard": 63,
        "aa_terminalbench_v21": 85,
        "aa_tau2": 99,
        "aa_tau3_banking": 27,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 61,
        "aa_non_hallucination_rate": 45,
        "aa_hle": 53,
        "aa_gpqa": 93,
        "aa_scicode": 60,
        "aa_ifbench": 63,
        "aa_critpt": 29,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 10,
        "aa_output_cost_usd_per_1m": 50,
        "aa_blended_cost_usd_per_1m": 26,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 71,
        "aa_speed_p5_tokens_per_second": 51,
        "aa_speed_p25_tokens_per_second": 57,
        "aa_speed_p75_tokens_per_second": 74,
        "aa_speed_p95_tokens_per_second": 98,
        "aa_latency_seconds": 112.25,
        "aa_latency_first_token_seconds": 112.25,
        "aa_latency_p5_seconds": 18.01,
        "aa_latency_p25_seconds": 64.06,
        "aa_latency_p75_seconds": 205.66,
        "aa_latency_p95_seconds": 252.37,
        "aa_total_response_time_seconds": 119.25,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 60,
        "llmdex_cost_index": 74,
        "llmdex_speed_index": 7.1,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 53.62,
        "llmdex_efficiency_score": 3.89,
        "llmdex_performance_rank": 3,
        "llmdex_value_rank": 77,
        "llmdex_efficiency_rank": 87,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-4-7:high-non-reasoning",
        "family_id": "anthropic/claude-opus-4-7",
        "variant_id": "anthropic/claude-opus-4-7:high-non-reasoning",
        "canonical_name": "Claude Opus 4.7 (Non-reasoning, high)",
        "source_name": "Claude Opus 4.7 (Non-reasoning, high)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-opus-4-7-non-reasoning-high",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-4-7-non-reasoning",
        "source_rank": 36,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 43,
        "aa_official_coding_index": 50,
        "aa_omniscience_index": 14,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 55,
        "aa_terminalbench_v21": null,
        "aa_tau2": 74,
        "aa_tau3_banking": null,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 44,
        "aa_non_hallucination_rate": 48,
        "aa_hle": 31,
        "aa_gpqa": 88,
        "aa_scicode": 50,
        "aa_ifbench": 44,
        "aa_critpt": 5,
        "aa_mmmu_pro": 76,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 45,
        "aa_speed_p5_tokens_per_second": 36,
        "aa_speed_p25_tokens_per_second": 40,
        "aa_speed_p75_tokens_per_second": 54,
        "aa_speed_p95_tokens_per_second": 82,
        "aa_latency_seconds": 1.59,
        "aa_latency_first_token_seconds": 1.59,
        "aa_latency_p5_seconds": 1.14,
        "aa_latency_p25_seconds": 1.48,
        "aa_latency_p75_seconds": 2.06,
        "aa_latency_p95_seconds": 3.25,
        "aa_total_response_time_seconds": 12.74,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 43,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 46.55,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.91,
        "llmdex_efficiency_score": 6.67,
        "llmdex_performance_rank": 36,
        "llmdex_value_rank": 41,
        "llmdex_efficiency_rank": 84,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-4-8:max",
        "family_id": "anthropic/claude-opus-4-8",
        "variant_id": "anthropic/claude-opus-4-8:max",
        "canonical_name": "Claude Opus 4.8 (max)",
        "source_name": "Claude Opus 4.8 (max)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-opus-4-8-max",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-4-8",
        "source_rank": 10,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 56,
        "aa_official_coding_index": 69,
        "aa_omniscience_index": 27,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 55,
        "aa_terminalbench_hard": 58,
        "aa_terminalbench_v21": 85,
        "aa_tau2": 94,
        "aa_tau3_banking": 28,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 47,
        "aa_non_hallucination_rate": 64,
        "aa_hle": 46,
        "aa_gpqa": 92,
        "aa_scicode": 53,
        "aa_ifbench": 62,
        "aa_critpt": 21,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 56,
        "aa_speed_p5_tokens_per_second": 39,
        "aa_speed_p25_tokens_per_second": 48,
        "aa_speed_p75_tokens_per_second": 69,
        "aa_speed_p95_tokens_per_second": 86,
        "aa_latency_seconds": 29.5,
        "aa_latency_first_token_seconds": 29.5,
        "aa_latency_p5_seconds": 4.26,
        "aa_latency_p25_seconds": 6.47,
        "aa_latency_p75_seconds": 75.88,
        "aa_latency_p95_seconds": 93.04,
        "aa_total_response_time_seconds": 38.42,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 56,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 5.6,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.22,
        "llmdex_efficiency_score": 10.83,
        "llmdex_performance_rank": 10,
        "llmdex_value_rank": 64,
        "llmdex_efficiency_rank": 77,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-5:high",
        "family_id": "anthropic/claude-opus-5",
        "variant_id": "anthropic/claude-opus-5:high",
        "canonical_name": "Claude Opus 5 (high)",
        "source_name": "Claude Opus 5 (high)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-opus-5-high",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-5-high",
        "source_rank": 5,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 59,
        "aa_official_coding_index": 71,
        "aa_omniscience_index": 28,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 62,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 88,
        "aa_tau2": null,
        "aa_tau3_banking": 33,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 53,
        "aa_non_hallucination_rate": 48,
        "aa_hle": 51,
        "aa_gpqa": 94,
        "aa_scicode": 54,
        "aa_ifbench": null,
        "aa_critpt": 28,
        "aa_mmmu_pro": 82,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 57,
        "aa_speed_p5_tokens_per_second": 44,
        "aa_speed_p25_tokens_per_second": 51,
        "aa_speed_p75_tokens_per_second": 66,
        "aa_speed_p95_tokens_per_second": 83,
        "aa_latency_seconds": 24.94,
        "aa_latency_first_token_seconds": 24.94,
        "aa_latency_p5_seconds": 3.77,
        "aa_latency_p25_seconds": 13.69,
        "aa_latency_p75_seconds": 32.02,
        "aa_latency_p95_seconds": 75.1,
        "aa_total_response_time_seconds": 33.66,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 59,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 5.7,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.74,
        "llmdex_efficiency_score": 12.78,
        "llmdex_performance_rank": 5,
        "llmdex_value_rank": 43,
        "llmdex_efficiency_rank": 74,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-5:low",
        "family_id": "anthropic/claude-opus-5",
        "variant_id": "anthropic/claude-opus-5:low",
        "canonical_name": "Claude Opus 5 (low)",
        "source_name": "Claude Opus 5 (low)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-opus-5-low",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-5-low",
        "source_rank": 19,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 51,
        "aa_official_coding_index": 62,
        "aa_omniscience_index": 23,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 48,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 76,
        "aa_tau2": null,
        "aa_tau3_banking": 23,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 50,
        "aa_non_hallucination_rate": 45,
        "aa_hle": 41,
        "aa_gpqa": 89,
        "aa_scicode": 48,
        "aa_ifbench": null,
        "aa_critpt": 23,
        "aa_mmmu_pro": 80,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 54,
        "aa_speed_p5_tokens_per_second": 43,
        "aa_speed_p25_tokens_per_second": 47,
        "aa_speed_p75_tokens_per_second": 61,
        "aa_speed_p95_tokens_per_second": 81,
        "aa_latency_seconds": 4.01,
        "aa_latency_first_token_seconds": 4.01,
        "aa_latency_p5_seconds": 2.02,
        "aa_latency_p25_seconds": 2.94,
        "aa_latency_p75_seconds": 4.94,
        "aa_latency_p95_seconds": 6.27,
        "aa_total_response_time_seconds": 13.22,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 51,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 35.35,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.67,
        "llmdex_efficiency_score": 8.89,
        "llmdex_performance_rank": 19,
        "llmdex_value_rank": 21,
        "llmdex_efficiency_rank": 80,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-5:max",
        "family_id": "anthropic/claude-opus-5",
        "variant_id": "anthropic/claude-opus-5:max",
        "canonical_name": "Claude Opus 5 (max)",
        "source_name": "Claude Opus 5 (max)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-opus-5-max",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-5",
        "source_rank": 1,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 61,
        "aa_official_coding_index": 72.5,
        "aa_omniscience_index": 31,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 68,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 89,
        "aa_tau2": null,
        "aa_tau3_banking": 30,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 54,
        "aa_non_hallucination_rate": 50,
        "aa_hle": 53,
        "aa_gpqa": 93,
        "aa_scicode": 56,
        "aa_ifbench": null,
        "aa_critpt": 29,
        "aa_mmmu_pro": 85,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 53,
        "aa_speed_p5_tokens_per_second": 41,
        "aa_speed_p25_tokens_per_second": 48,
        "aa_speed_p75_tokens_per_second": 64,
        "aa_speed_p95_tokens_per_second": 89,
        "aa_latency_seconds": 68.04,
        "aa_latency_first_token_seconds": 68.04,
        "aa_latency_p5_seconds": 22.79,
        "aa_latency_p25_seconds": 41.59,
        "aa_latency_p75_seconds": 118.14,
        "aa_latency_p95_seconds": 258.86,
        "aa_total_response_time_seconds": 77.55,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 61,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 5.3,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.66,
        "llmdex_efficiency_score": 14.44,
        "llmdex_performance_rank": 1,
        "llmdex_value_rank": 31,
        "llmdex_efficiency_rank": 72,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-5:medium",
        "family_id": "anthropic/claude-opus-5",
        "variant_id": "anthropic/claude-opus-5:medium",
        "canonical_name": "Claude Opus 5 (medium)",
        "source_name": "Claude Opus 5 (medium)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-opus-5-medium",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-5-medium",
        "source_rank": 8,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 56,
        "aa_official_coding_index": 68.5,
        "aa_omniscience_index": 26,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 57,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 86,
        "aa_tau2": null,
        "aa_tau3_banking": 29,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 51,
        "aa_non_hallucination_rate": 48,
        "aa_hle": 49,
        "aa_gpqa": 92,
        "aa_scicode": 51,
        "aa_ifbench": null,
        "aa_critpt": 27,
        "aa_mmmu_pro": 82,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 52,
        "aa_speed_p5_tokens_per_second": 43,
        "aa_speed_p25_tokens_per_second": 46,
        "aa_speed_p75_tokens_per_second": 56,
        "aa_speed_p95_tokens_per_second": 78,
        "aa_latency_seconds": 5.3,
        "aa_latency_first_token_seconds": 5.3,
        "aa_latency_p5_seconds": 1.85,
        "aa_latency_p25_seconds": 3.88,
        "aa_latency_p75_seconds": 17.49,
        "aa_latency_p95_seconds": 28.46,
        "aa_total_response_time_seconds": 14.96,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 56,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 28.7,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 59.84,
        "llmdex_efficiency_score": 10.83,
        "llmdex_performance_rank": 8,
        "llmdex_value_rank": 14,
        "llmdex_efficiency_rank": 78,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-opus-5:xhigh",
        "family_id": "anthropic/claude-opus-5",
        "variant_id": "anthropic/claude-opus-5:xhigh",
        "canonical_name": "Claude Opus 5 (xhigh)",
        "source_name": "Claude Opus 5 (xhigh)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-opus-5-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/claude-opus-5-xhigh",
        "source_rank": 2,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 60,
        "aa_official_coding_index": 71.5,
        "aa_omniscience_index": 30,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 66,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 88,
        "aa_tau2": null,
        "aa_tau3_banking": 32,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 53,
        "aa_non_hallucination_rate": 50,
        "aa_hle": 53,
        "aa_gpqa": 94,
        "aa_scicode": 55,
        "aa_ifbench": null,
        "aa_critpt": 28,
        "aa_mmmu_pro": 84,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 25,
        "aa_blended_cost_usd_per_1m": 13,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 53,
        "aa_speed_p5_tokens_per_second": 40,
        "aa_speed_p25_tokens_per_second": 48,
        "aa_speed_p75_tokens_per_second": 62,
        "aa_speed_p95_tokens_per_second": 88,
        "aa_latency_seconds": 33.21,
        "aa_latency_first_token_seconds": 33.21,
        "aa_latency_p5_seconds": 3.96,
        "aa_latency_p25_seconds": 14.67,
        "aa_latency_p75_seconds": 68.1,
        "aa_latency_p95_seconds": 173.11,
        "aa_total_response_time_seconds": 42.68,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 60,
        "llmdex_cost_index": 87,
        "llmdex_speed_index": 5.3,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.16,
        "llmdex_efficiency_score": 13.33,
        "llmdex_performance_rank": 2,
        "llmdex_value_rank": 38,
        "llmdex_efficiency_rank": 73,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-4-6:low-non-reasoning",
        "family_id": "anthropic/claude-sonnet-4-6",
        "variant_id": "anthropic/claude-sonnet-4-6:low-non-reasoning",
        "canonical_name": "Claude Sonnet 4.6 (Non-reasoning, Low Effort)",
        "source_name": "Claude Sonnet 4.6 (Non-reasoning, Low Effort)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-sonnet-4-6-non-reasoning-low-effort",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-4-6-non-reasoning-low-effort",
        "source_rank": 62,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 44,
        "aa_omniscience_index": -2,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 42,
        "aa_terminalbench_v21": null,
        "aa_tau2": 79,
        "aa_tau3_banking": null,
        "aa_lcr": 59,
        "aa_omniscience_accuracy": 36,
        "aa_non_hallucination_rate": 40,
        "aa_hle": 11,
        "aa_gpqa": 80,
        "aa_scicode": 44,
        "aa_ifbench": 42,
        "aa_critpt": 1,
        "aa_mmmu_pro": 69,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 3,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 44,
        "aa_speed_p5_tokens_per_second": 37,
        "aa_speed_p25_tokens_per_second": 39,
        "aa_speed_p75_tokens_per_second": 51,
        "aa_speed_p95_tokens_per_second": 82,
        "aa_latency_seconds": 1.37,
        "aa_latency_first_token_seconds": 1.37,
        "aa_latency_p5_seconds": 1.06,
        "aa_latency_p25_seconds": 1.22,
        "aa_latency_p75_seconds": 1.75,
        "aa_latency_p95_seconds": 4.94,
        "aa_total_response_time_seconds": 12.8,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 92.2,
        "llmdex_speed_index": 47.55,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.17,
        "llmdex_efficiency_score": 11.67,
        "llmdex_performance_rank": 62,
        "llmdex_value_rank": 72,
        "llmdex_efficiency_rank": 76,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:high",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:high",
        "canonical_name": "Claude Sonnet 5 (high)",
        "source_name": "Claude Sonnet 5 (high)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-sonnet-5-high",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5-high",
        "source_rank": 260,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 45,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 63,
        "aa_speed_p5_tokens_per_second": 48,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 88,
        "aa_speed_p95_tokens_per_second": 115,
        "aa_latency_seconds": 14.23,
        "aa_latency_first_token_seconds": 14.23,
        "aa_latency_p5_seconds": 1.08,
        "aa_latency_p25_seconds": 4.31,
        "aa_latency_p75_seconds": 22.92,
        "aa_latency_p95_seconds": 35.4,
        "aa_total_response_time_seconds": 22.16,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 6.3,
        "llmdex_coverage_score": 37.5,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:low",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:low",
        "canonical_name": "Claude Sonnet 5 (low)",
        "source_name": "Claude Sonnet 5 (low)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-sonnet-5-low",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5-low",
        "source_rank": 256,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 36,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 63,
        "aa_speed_p5_tokens_per_second": 49,
        "aa_speed_p25_tokens_per_second": 54,
        "aa_speed_p75_tokens_per_second": 75,
        "aa_speed_p95_tokens_per_second": 113,
        "aa_latency_seconds": 1.65,
        "aa_latency_first_token_seconds": 1.65,
        "aa_latency_p5_seconds": 0.92,
        "aa_latency_p25_seconds": 1.26,
        "aa_latency_p75_seconds": 2.12,
        "aa_latency_p95_seconds": 3.94,
        "aa_total_response_time_seconds": 9.64,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 48.05,
        "llmdex_coverage_score": 37.5,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:max",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:max",
        "canonical_name": "Claude Sonnet 5 (max)",
        "source_name": "Claude Sonnet 5 (max)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "claude-sonnet-5-max",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5",
        "source_rank": 14,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 53,
        "aa_official_coding_index": 67.5,
        "aa_omniscience_index": 15,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 55,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 81,
        "aa_tau2": null,
        "aa_tau3_banking": 28,
        "aa_lcr": 71,
        "aa_omniscience_accuracy": 38,
        "aa_non_hallucination_rate": 63,
        "aa_hle": 40,
        "aa_gpqa": 91,
        "aa_scicode": 54,
        "aa_ifbench": null,
        "aa_critpt": 17,
        "aa_mmmu_pro": 77,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 76,
        "aa_speed_p5_tokens_per_second": 57,
        "aa_speed_p25_tokens_per_second": 66,
        "aa_speed_p75_tokens_per_second": 88,
        "aa_speed_p95_tokens_per_second": 95,
        "aa_latency_seconds": 192.06,
        "aa_latency_first_token_seconds": 192.06,
        "aa_latency_p5_seconds": 43.35,
        "aa_latency_p25_seconds": 140.5,
        "aa_latency_p75_seconds": 273.71,
        "aa_latency_p95_seconds": 301.74,
        "aa_total_response_time_seconds": 198.64,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 53,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 7.6,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.46,
        "llmdex_efficiency_score": 30.56,
        "llmdex_performance_rank": 14,
        "llmdex_value_rank": 47,
        "llmdex_efficiency_rank": 56,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:medium",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:medium",
        "canonical_name": "Claude Sonnet 5 (medium)",
        "source_name": "Claude Sonnet 5 (medium)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-sonnet-5-medium",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5-medium",
        "source_rank": 264,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 40,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 63,
        "aa_speed_p5_tokens_per_second": 47,
        "aa_speed_p25_tokens_per_second": 55,
        "aa_speed_p75_tokens_per_second": 73,
        "aa_speed_p95_tokens_per_second": 117,
        "aa_latency_seconds": 1.89,
        "aa_latency_first_token_seconds": 1.89,
        "aa_latency_p5_seconds": 0.91,
        "aa_latency_p25_seconds": 1.31,
        "aa_latency_p75_seconds": 4.77,
        "aa_latency_p95_seconds": 14.9,
        "aa_total_response_time_seconds": 9.78,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 46.85,
        "llmdex_coverage_score": 37.5,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:non-reasoning",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:non-reasoning",
        "canonical_name": "Claude Sonnet 5 (Non-reasoning)",
        "source_name": "Claude Sonnet 5 (Non-reasoning)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-sonnet-5-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5-non-reasoning",
        "source_rank": 39,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 42,
        "aa_official_coding_index": 62,
        "aa_omniscience_index": -1,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 43,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 75,
        "aa_tau2": null,
        "aa_tau3_banking": 14,
        "aa_lcr": 59,
        "aa_omniscience_accuracy": 33,
        "aa_non_hallucination_rate": 50,
        "aa_hle": 18,
        "aa_gpqa": 80,
        "aa_scicode": 49,
        "aa_ifbench": null,
        "aa_critpt": 1,
        "aa_mmmu_pro": 72,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 58,
        "aa_speed_p5_tokens_per_second": 48,
        "aa_speed_p25_tokens_per_second": 52,
        "aa_speed_p75_tokens_per_second": 73,
        "aa_speed_p95_tokens_per_second": 102,
        "aa_latency_seconds": 1.37,
        "aa_latency_first_token_seconds": 1.37,
        "aa_latency_p5_seconds": 0.81,
        "aa_latency_p25_seconds": 0.96,
        "aa_latency_p75_seconds": 1.66,
        "aa_latency_p95_seconds": 3.98,
        "aa_total_response_time_seconds": 10.01,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 42,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 48.95,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 59.23,
        "llmdex_efficiency_score": 25,
        "llmdex_performance_rank": 39,
        "llmdex_value_rank": 18,
        "llmdex_efficiency_rank": 59,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "anthropic/claude-sonnet-5:xhigh",
        "family_id": "anthropic/claude-sonnet-5",
        "variant_id": "anthropic/claude-sonnet-5:xhigh",
        "canonical_name": "Claude Sonnet 5 (xhigh)",
        "source_name": "Claude Sonnet 5 (xhigh)",
        "provider": "Anthropic",
        "creator": "Anthropic",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "claude-sonnet-5-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/claude-sonnet-5-xhigh",
        "source_rank": 258,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 50,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 66,
        "aa_speed_p5_tokens_per_second": 47,
        "aa_speed_p25_tokens_per_second": 51,
        "aa_speed_p75_tokens_per_second": 91,
        "aa_speed_p95_tokens_per_second": 119,
        "aa_latency_seconds": 29.93,
        "aa_latency_first_token_seconds": 29.93,
        "aa_latency_p5_seconds": 5.61,
        "aa_latency_p25_seconds": 9.31,
        "aa_latency_p75_seconds": 57.21,
        "aa_latency_p95_seconds": 123.17,
        "aa_total_response_time_seconds": 37.47,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": 94.8,
        "llmdex_speed_index": 6.6,
        "llmdex_coverage_score": 37.5,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "arcee-ai/trinity-large:thinking",
        "family_id": "arcee-ai/trinity-large",
        "variant_id": "arcee-ai/trinity-large:thinking",
        "canonical_name": "Trinity Large Thinking",
        "source_name": "Trinity Large Thinking",
        "provider": "Arcee AI",
        "creator": "Arcee AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "trinity-large-thinking",
        "source_model_url": "https://artificialanalysis.ai/models/trinity-large-thinking",
        "source_rank": 127,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 28.5,
        "aa_omniscience_index": -44,
        "aa_context_window_tokens": 512000,
        "aa_gdpval": 3,
        "aa_terminalbench_hard": 23,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 90,
        "aa_tau3_banking": 6,
        "aa_lcr": 33,
        "aa_omniscience_accuracy": 23,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 15,
        "aa_gpqa": 75,
        "aa_scicode": 36,
        "aa_ifbench": 56,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.23,
        "aa_output_cost_usd_per_1m": 0.88,
        "aa_blended_cost_usd_per_1m": 0.49,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 172,
        "aa_speed_p5_tokens_per_second": 105,
        "aa_speed_p25_tokens_per_second": 153,
        "aa_speed_p75_tokens_per_second": 197,
        "aa_speed_p95_tokens_per_second": 210,
        "aa_latency_seconds": 0.88,
        "aa_latency_first_token_seconds": 12.51,
        "aa_latency_p5_seconds": 0.8,
        "aa_latency_p25_seconds": 0.85,
        "aa_latency_p75_seconds": 1,
        "aa_latency_p95_seconds": 1.96,
        "aa_total_response_time_seconds": 15.42,
        "aa_reasoning_time_seconds": 11.63,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": 99.51,
        "llmdex_speed_index": 62.8,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 51.41,
        "llmdex_efficiency_score": 63.33,
        "llmdex_performance_rank": 127,
        "llmdex_value_rank": 95,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "baidu/ernie-4-5-300b-a47b:default",
        "family_id": "baidu/ernie-4-5-300b-a47b",
        "variant_id": "baidu/ernie-4-5-300b-a47b:default",
        "canonical_name": "ERNIE 4.5 300B A47B",
        "source_name": "ERNIE 4.5 300B A47B",
        "provider": "Baidu",
        "creator": "Baidu",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ernie-4-5-300b-a47b",
        "source_model_url": "https://artificialanalysis.ai/models/ernie-4-5-300b-a47b",
        "source_rank": 183,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 31,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 6,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 2,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 33,
        "aa_hle": 4,
        "aa_gpqa": 81,
        "aa_scicode": 31,
        "aa_ifbench": 39,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.28,
        "aa_output_cost_usd_per_1m": 1.1,
        "aa_blended_cost_usd_per_1m": 0.608,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 42.9,
        "llmdex_efficiency_score": 39.44,
        "llmdex_performance_rank": 183,
        "llmdex_value_rank": 151,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "baidu/ernie-5-0-thinking-preview:thinking-preview",
        "family_id": "baidu/ernie-5-0-thinking-preview",
        "variant_id": "baidu/ernie-5-0-thinking-preview:thinking-preview",
        "canonical_name": "ERNIE 5.0 Thinking Preview",
        "source_name": "ERNIE 5.0 Thinking Preview",
        "provider": "Baidu",
        "creator": "Baidu",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "ernie-5-0-thinking-preview",
        "source_model_url": "https://artificialanalysis.ai/models/ernie-5-0-thinking-preview",
        "source_rank": 106,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 22,
        "aa_official_coding_index": 38,
        "aa_omniscience_index": -44,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 25,
        "aa_terminalbench_v21": null,
        "aa_tau2": 84,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 13,
        "aa_gpqa": 78,
        "aa_scicode": 38,
        "aa_ifbench": 41,
        "aa_critpt": 1,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 22,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 22,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 106,
        "llmdex_value_rank": 192,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "bytedance-seed/doubao-seed-code:default",
        "family_id": "bytedance-seed/doubao-seed-code",
        "variant_id": "bytedance-seed/doubao-seed-code:default",
        "canonical_name": "Doubao Seed Code",
        "source_name": "Doubao Seed Code",
        "provider": "ByteDance Seed",
        "creator": "ByteDance Seed",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "doubao-seed-code",
        "source_model_url": "https://artificialanalysis.ai/models/doubao-seed-code",
        "source_rank": 93,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -34,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": null,
        "aa_tau2": 58,
        "aa_tau3_banking": null,
        "aa_lcr": 65,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 21,
        "aa_hle": 13,
        "aa_gpqa": 76,
        "aa_scicode": 41,
        "aa_ifbench": 51,
        "aa_critpt": 0,
        "aa_mmmu_pro": 68,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 26,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 93,
        "llmdex_value_rank": 190,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "china-mobile/jt-35b-flash:default",
        "family_id": "china-mobile/jt-35b-flash",
        "variant_id": "china-mobile/jt-35b-flash:default",
        "canonical_name": "JT-35B-Flash",
        "source_name": "JT-35B-Flash",
        "provider": "China Mobile",
        "creator": "China Mobile",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "jt-35b-flash",
        "source_model_url": "https://artificialanalysis.ai/models/jt-35b-flash",
        "source_rank": 85,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 28,
        "aa_official_coding_index": 29,
        "aa_omniscience_index": -23,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 29,
        "aa_terminalbench_v21": null,
        "aa_tau2": 99,
        "aa_tau3_banking": null,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 37,
        "aa_hle": 6,
        "aa_gpqa": 83,
        "aa_scicode": 29,
        "aa_ifbench": 42,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 28,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 28,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 85,
        "llmdex_value_rank": 188,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "china-mobile/jt-4-1-flash-236b-a21b:default",
        "family_id": "china-mobile/jt-4-1-flash-236b-a21b",
        "variant_id": "china-mobile/jt-4-1-flash-236b-a21b:default",
        "canonical_name": "JT-4.1 Flash 236B A21B",
        "source_name": "JT-4.1 Flash 236B A21B",
        "provider": "China Mobile",
        "creator": "China Mobile",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "jt-4-1-flash-236b-a21b",
        "source_model_url": "https://artificialanalysis.ai/models/jt-4-1-flash-236b-a21b",
        "source_rank": 48,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 39,
        "aa_official_coding_index": 49,
        "aa_omniscience_index": -10,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 38,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 60,
        "aa_tau2": null,
        "aa_tau3_banking": 28,
        "aa_lcr": 59,
        "aa_omniscience_accuracy": 23,
        "aa_non_hallucination_rate": 57,
        "aa_hle": 16,
        "aa_gpqa": 85,
        "aa_scicode": 38,
        "aa_ifbench": null,
        "aa_critpt": 0,
        "aa_mmmu_pro": 64,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 39,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 39,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 48,
        "llmdex_value_rank": 175,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "china-mobile/jt-mini:default",
        "family_id": "china-mobile/jt-mini",
        "variant_id": "china-mobile/jt-mini:default",
        "canonical_name": "JT-MINI",
        "source_name": "JT-MINI",
        "provider": "China Mobile",
        "creator": "China Mobile",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "jt-mini",
        "source_model_url": "https://artificialanalysis.ai/models/jt-mini",
        "source_rank": 125,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 19,
        "aa_official_coding_index": 27,
        "aa_omniscience_index": -65,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 18,
        "aa_terminalbench_v21": null,
        "aa_tau2": 93,
        "aa_tau3_banking": null,
        "aa_lcr": 12,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 7,
        "aa_gpqa": 68,
        "aa_scicode": 27,
        "aa_ifbench": 37,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 19,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 19,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 125,
        "llmdex_value_rank": 196,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "cohere/command-a:default:command-a",
        "family_id": "cohere/command-a",
        "variant_id": "cohere/command-a:default",
        "canonical_name": "Command A+",
        "source_name": "Command A+",
        "provider": "Cohere",
        "creator": "Cohere",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "command-a",
        "source_model_url": "https://artificialanalysis.ai/models/command-a-plus",
        "source_rank": 104,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 23,
        "aa_official_coding_index": 30.5,
        "aa_omniscience_index": -4,
        "aa_context_window_tokens": 192000,
        "aa_gdpval": 11,
        "aa_terminalbench_hard": 25,
        "aa_terminalbench_v21": 23,
        "aa_tau2": 81,
        "aa_tau3_banking": 6,
        "aa_lcr": 46,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 86,
        "aa_hle": 11,
        "aa_gpqa": 76,
        "aa_scicode": 38,
        "aa_ifbench": 74,
        "aa_critpt": 0,
        "aa_mmmu_pro": 63,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 196,
        "aa_speed_p5_tokens_per_second": 158,
        "aa_speed_p25_tokens_per_second": 186,
        "aa_speed_p75_tokens_per_second": 206,
        "aa_speed_p95_tokens_per_second": 223,
        "aa_latency_seconds": 0.42,
        "aa_latency_first_token_seconds": 10.6,
        "aa_latency_p5_seconds": 0.36,
        "aa_latency_p25_seconds": 0.38,
        "aa_latency_p75_seconds": 0.55,
        "aa_latency_p95_seconds": 1.61,
        "aa_total_response_time_seconds": 13.14,
        "aa_reasoning_time_seconds": 10.18,
        "llmdex_adjusted_performance": 23,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 67.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 104,
        "llmdex_value_rank": 66,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "cohere/north-mini-code:default",
        "family_id": "cohere/north-mini-code",
        "variant_id": "cohere/north-mini-code:default",
        "canonical_name": "North Mini Code",
        "source_name": "North Mini Code",
        "provider": "Cohere",
        "creator": "Cohere",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "north-mini-code",
        "source_model_url": "https://artificialanalysis.ai/models/north-mini-code",
        "source_rank": 119,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -49,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 2,
        "aa_terminalbench_hard": 31,
        "aa_terminalbench_v21": 36,
        "aa_tau2": 37,
        "aa_tau3_banking": 6,
        "aa_lcr": 32,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 17,
        "aa_hle": 10,
        "aa_gpqa": 76,
        "aa_scicode": 38,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 67,
        "aa_speed_p5_tokens_per_second": 30,
        "aa_speed_p25_tokens_per_second": 42,
        "aa_speed_p75_tokens_per_second": 100,
        "aa_speed_p95_tokens_per_second": 151,
        "aa_latency_seconds": 0.58,
        "aa_latency_first_token_seconds": 30.47,
        "aa_latency_p5_seconds": 0.29,
        "aa_latency_p25_seconds": 0.35,
        "aa_latency_p75_seconds": 1.04,
        "aa_latency_p95_seconds": 2.05,
        "aa_total_response_time_seconds": 37.94,
        "aa_reasoning_time_seconds": 29.89,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 53.8,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.76,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 119,
        "llmdex_value_rank": 99,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "cohere/tiny-aya-global:default",
        "family_id": "cohere/tiny-aya-global",
        "variant_id": "cohere/tiny-aya-global:default",
        "canonical_name": "Tiny Aya Global",
        "source_name": "Tiny Aya Global",
        "provider": "Cohere",
        "creator": "Cohere",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "tiny-aya-global",
        "source_model_url": "https://artificialanalysis.ai/models/tiny-aya-global",
        "source_rank": 253,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 1,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": -85,
        "aa_context_window_tokens": 8189,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 5,
        "aa_gpqa": 31,
        "aa_scicode": 4,
        "aa_ifbench": 20,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 1,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 38.12,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 253,
        "llmdex_value_rank": 179,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deep-cogito/cogito-v2-1:reasoning",
        "family_id": "deep-cogito/cogito-v2-1",
        "variant_id": "deep-cogito/cogito-v2-1:reasoning",
        "canonical_name": "Cogito v2.1 (reasoning)",
        "source_name": "Cogito v2.1 (reasoning)",
        "provider": "Deep Cogito",
        "creator": "Deep Cogito",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "cogito-v2-1-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/cogito-v2-1-reasoning",
        "source_rank": 263,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -25,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": 22,
        "aa_omniscience_accuracy": 30,
        "aa_non_hallucination_rate": 21,
        "aa_hle": 11,
        "aa_gpqa": 77,
        "aa_scicode": 41,
        "aa_ifbench": 46,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 1.25,
        "aa_blended_cost_usd_per_1m": 1.25,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": 98.75,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-flash:high",
        "family_id": "deepseek/deepseek-v4-flash",
        "variant_id": "deepseek/deepseek-v4-flash:high",
        "canonical_name": "DeepSeek V4 Flash (high)",
        "source_name": "DeepSeek V4 Flash (high)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "deepseek-v4-flash-high",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-flash-high",
        "source_rank": 52,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 37,
        "aa_official_coding_index": 49.5,
        "aa_omniscience_index": -22,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": 39,
        "aa_terminalbench_v21": 57,
        "aa_tau2": 96,
        "aa_tau3_banking": 20,
        "aa_lcr": 63,
        "aa_omniscience_accuracy": 36,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 28,
        "aa_gpqa": 87,
        "aa_scicode": 42,
        "aa_ifbench": 73,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.28,
        "aa_blended_cost_usd_per_1m": 0.196,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 37,
        "llmdex_cost_index": 99.8,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 59.4,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 60.55,
        "llmdex_efficiency_score": 88.61,
        "llmdex_performance_rank": 52,
        "llmdex_value_rank": 13,
        "llmdex_efficiency_rank": 5,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-flash:max",
        "family_id": "deepseek/deepseek-v4-flash",
        "variant_id": "deepseek/deepseek-v4-flash:max",
        "canonical_name": "DeepSeek V4 Flash (max)",
        "source_name": "DeepSeek V4 Flash (max)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "deepseek-v4-flash-max",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-flash",
        "source_rank": 45,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 40,
        "aa_official_coding_index": 53.5,
        "aa_omniscience_index": -23,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 34,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": 62,
        "aa_tau2": 95,
        "aa_tau3_banking": 23,
        "aa_lcr": 63,
        "aa_omniscience_accuracy": 37,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 32,
        "aa_gpqa": 89,
        "aa_scicode": 45,
        "aa_ifbench": 79,
        "aa_critpt": 7,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": 32,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.28,
        "aa_blended_cost_usd_per_1m": 0.196,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 121,
        "aa_speed_p5_tokens_per_second": 75,
        "aa_speed_p25_tokens_per_second": 90,
        "aa_speed_p75_tokens_per_second": 134,
        "aa_speed_p95_tokens_per_second": 145,
        "aa_latency_seconds": 1.16,
        "aa_latency_first_token_seconds": 47.38,
        "aa_latency_p5_seconds": 1,
        "aa_latency_p25_seconds": 1.07,
        "aa_latency_p75_seconds": 1.4,
        "aa_latency_p95_seconds": 2.51,
        "aa_total_response_time_seconds": 51.49,
        "aa_reasoning_time_seconds": 46.22,
        "llmdex_adjusted_performance": 40,
        "llmdex_cost_index": 99.8,
        "llmdex_speed_index": 56.3,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.2,
        "llmdex_efficiency_score": 90,
        "llmdex_performance_rank": 45,
        "llmdex_value_rank": 8,
        "llmdex_efficiency_rank": 3,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-flash:non-reasoning",
        "family_id": "deepseek/deepseek-v4-flash",
        "variant_id": "deepseek/deepseek-v4-flash:non-reasoning",
        "canonical_name": "DeepSeek V4 Flash (non-reasoning)",
        "source_name": "DeepSeek V4 Flash (non-reasoning)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "deepseek-v4-flash-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-flash-non-reasoning",
        "source_rank": 84,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 29,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -44,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 34,
        "aa_terminalbench_v21": null,
        "aa_tau2": 94,
        "aa_tau3_banking": null,
        "aa_lcr": 33,
        "aa_omniscience_accuracy": 26,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 7,
        "aa_gpqa": 72,
        "aa_scicode": 37,
        "aa_ifbench": 47,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.28,
        "aa_blended_cost_usd_per_1m": 0.196,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 116,
        "aa_speed_p5_tokens_per_second": 75,
        "aa_speed_p25_tokens_per_second": 90,
        "aa_speed_p75_tokens_per_second": 143,
        "aa_speed_p95_tokens_per_second": 158,
        "aa_latency_seconds": 1.22,
        "aa_latency_first_token_seconds": 1.22,
        "aa_latency_p5_seconds": 1.05,
        "aa_latency_p25_seconds": 1.13,
        "aa_latency_p75_seconds": 1.33,
        "aa_latency_p95_seconds": 1.63,
        "aa_total_response_time_seconds": 5.53,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 29,
        "llmdex_cost_index": 99.8,
        "llmdex_speed_index": 55.5,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.54,
        "llmdex_efficiency_score": 87.22,
        "llmdex_performance_rank": 84,
        "llmdex_value_rank": 60,
        "llmdex_efficiency_rank": 7,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-pro:high",
        "family_id": "deepseek/deepseek-v4-pro",
        "variant_id": "deepseek/deepseek-v4-pro:high",
        "canonical_name": "DeepSeek V4 Pro (high)",
        "source_name": "DeepSeek V4 Pro (high)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "deepseek-v4-pro-high",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-pro-high",
        "source_rank": 34,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 43,
        "aa_official_coding_index": 55.5,
        "aa_omniscience_index": -10,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 40,
        "aa_terminalbench_hard": 42,
        "aa_terminalbench_v21": 65,
        "aa_tau2": 94,
        "aa_tau3_banking": 24,
        "aa_lcr": 65,
        "aa_omniscience_accuracy": 42,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 34,
        "aa_gpqa": 91,
        "aa_scicode": 46,
        "aa_ifbench": 71,
        "aa_critpt": 10,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.43,
        "aa_output_cost_usd_per_1m": 0.87,
        "aa_blended_cost_usd_per_1m": 0.606,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 65,
        "aa_speed_p5_tokens_per_second": 42,
        "aa_speed_p25_tokens_per_second": 56,
        "aa_speed_p75_tokens_per_second": 80,
        "aa_speed_p95_tokens_per_second": 94,
        "aa_latency_seconds": 1.57,
        "aa_latency_first_token_seconds": 32.33,
        "aa_latency_p5_seconds": 1.14,
        "aa_latency_p25_seconds": 1.43,
        "aa_latency_p75_seconds": 1.74,
        "aa_latency_p95_seconds": 1.94,
        "aa_total_response_time_seconds": 40.06,
        "aa_reasoning_time_seconds": 30.77,
        "llmdex_adjusted_performance": 43,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": 48.65,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.05,
        "llmdex_efficiency_score": 76.11,
        "llmdex_performance_rank": 34,
        "llmdex_value_rank": 11,
        "llmdex_efficiency_rank": 12,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-pro:max",
        "family_id": "deepseek/deepseek-v4-pro",
        "variant_id": "deepseek/deepseek-v4-pro:max",
        "canonical_name": "DeepSeek V4 Pro (max)",
        "source_name": "DeepSeek V4 Pro (max)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "deepseek-v4-pro-max",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-pro",
        "source_rank": 31,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 44,
        "aa_official_coding_index": 57,
        "aa_omniscience_index": -10,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 40,
        "aa_terminalbench_hard": 46,
        "aa_terminalbench_v21": 64,
        "aa_tau2": 96,
        "aa_tau3_banking": 26,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 43,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 36,
        "aa_gpqa": 89,
        "aa_scicode": 50,
        "aa_ifbench": 76,
        "aa_critpt": 13,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 24,
        "aa_itbench": 38,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.43,
        "aa_output_cost_usd_per_1m": 0.87,
        "aa_blended_cost_usd_per_1m": 0.606,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 67,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 56,
        "aa_speed_p75_tokens_per_second": 82,
        "aa_speed_p95_tokens_per_second": 93,
        "aa_latency_seconds": 1.61,
        "aa_latency_first_token_seconds": 67.3,
        "aa_latency_p5_seconds": 0.99,
        "aa_latency_p25_seconds": 1.43,
        "aa_latency_p75_seconds": 1.83,
        "aa_latency_p95_seconds": 2.34,
        "aa_total_response_time_seconds": 74.81,
        "aa_reasoning_time_seconds": 65.69,
        "llmdex_adjusted_performance": 44,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": 48.65,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.55,
        "llmdex_efficiency_score": 77.22,
        "llmdex_performance_rank": 31,
        "llmdex_value_rank": 6,
        "llmdex_efficiency_rank": 11,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "deepseek/deepseek-v4-pro:non-reasoning",
        "family_id": "deepseek/deepseek-v4-pro",
        "variant_id": "deepseek/deepseek-v4-pro:non-reasoning",
        "canonical_name": "DeepSeek V4 Pro (non-reasoning)",
        "source_name": "DeepSeek V4 Pro (non-reasoning)",
        "provider": "DeepSeek",
        "creator": "DeepSeek",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "deepseek-v4-pro-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/deepseek-v4-pro-non-reasoning",
        "source_rank": 74,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 31,
        "aa_official_coding_index": 42,
        "aa_omniscience_index": -30,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": null,
        "aa_tau2": 91,
        "aa_tau3_banking": null,
        "aa_lcr": 45,
        "aa_omniscience_accuracy": 31,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 8,
        "aa_gpqa": 72,
        "aa_scicode": 42,
        "aa_ifbench": 46,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.43,
        "aa_output_cost_usd_per_1m": 0.87,
        "aa_blended_cost_usd_per_1m": 0.606,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 70,
        "aa_speed_p5_tokens_per_second": 43,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 87,
        "aa_speed_p95_tokens_per_second": 102,
        "aa_latency_seconds": 1.46,
        "aa_latency_first_token_seconds": 1.46,
        "aa_latency_p5_seconds": 0.93,
        "aa_latency_p25_seconds": 1.24,
        "aa_latency_p75_seconds": 1.58,
        "aa_latency_p95_seconds": 1.68,
        "aa_total_response_time_seconds": 8.57,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 31,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": 49.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.26,
        "llmdex_efficiency_score": 68.33,
        "llmdex_performance_rank": 74,
        "llmdex_value_rank": 63,
        "llmdex_efficiency_rank": 19,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/diffusiongemma-26b-a4b:default",
        "family_id": "google/diffusiongemma-26b-a4b",
        "variant_id": "google/diffusiongemma-26b-a4b:default",
        "canonical_name": "DiffusionGemma 26B A4B",
        "source_name": "DiffusionGemma 26B A4B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "diffusiongemma-26b-a4b",
        "source_model_url": "https://artificialanalysis.ai/models/diffusiongemma-26b-a4b",
        "source_rank": 157,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 13,
        "aa_official_coding_index": 23,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 3,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 12,
        "aa_tau2": null,
        "aa_tau3_banking": 7,
        "aa_lcr": 14,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 10,
        "aa_gpqa": 67,
        "aa_scicode": 34,
        "aa_ifbench": 59,
        "aa_critpt": 0,
        "aa_mmmu_pro": 67,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 13,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 13,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 157,
        "llmdex_value_rank": 208,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-2-5-pro:default",
        "family_id": "google/gemini-2-5-pro",
        "variant_id": "google/gemini-2-5-pro:default",
        "canonical_name": "Gemini 2.5 Pro",
        "source_name": "Gemini 2.5 Pro",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-2-5-pro",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-2-5-pro",
        "source_rank": 94,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 35.5,
        "aa_omniscience_index": -14,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 9,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": 28,
        "aa_tau2": 54,
        "aa_tau3_banking": 9,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 39,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 21,
        "aa_gpqa": 84,
        "aa_scicode": 43,
        "aa_ifbench": 49,
        "aa_critpt": 3,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 4.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 128,
        "aa_speed_p5_tokens_per_second": 104,
        "aa_speed_p25_tokens_per_second": 120,
        "aa_speed_p75_tokens_per_second": 152,
        "aa_speed_p95_tokens_per_second": 162,
        "aa_latency_seconds": 23.37,
        "aa_latency_first_token_seconds": 23.37,
        "aa_latency_p5_seconds": 13.95,
        "aa_latency_p25_seconds": 19.43,
        "aa_latency_p75_seconds": 27.59,
        "aa_latency_p95_seconds": 33.61,
        "aa_total_response_time_seconds": 27.28,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": 95.25,
        "llmdex_speed_index": 12.8,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 44.14,
        "llmdex_efficiency_score": 16.67,
        "llmdex_performance_rank": 94,
        "llmdex_value_rank": 143,
        "llmdex_efficiency_rank": 70,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-1-flash-lite:default",
        "family_id": "google/gemini-3-1-flash-lite",
        "variant_id": "google/gemini-3-1-flash-lite:default",
        "canonical_name": "Gemini 3.1 Flash-Lite",
        "source_name": "Gemini 3.1 Flash-Lite",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-1-flash-lite",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-1-flash-lite-preview",
        "source_rank": 97,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 25,
        "aa_official_coding_index": 36.5,
        "aa_omniscience_index": -16,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 7,
        "aa_terminalbench_hard": 24,
        "aa_terminalbench_v21": 31,
        "aa_tau2": 31,
        "aa_tau3_banking": 9,
        "aa_lcr": 65,
        "aa_omniscience_accuracy": 36,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 16,
        "aa_gpqa": 82,
        "aa_scicode": 42,
        "aa_ifbench": 77,
        "aa_critpt": 1,
        "aa_mmmu_pro": 76,
        "aa_apex_agents": 12,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 1.5,
        "aa_blended_cost_usd_per_1m": 0.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 293,
        "aa_speed_p5_tokens_per_second": 211,
        "aa_speed_p25_tokens_per_second": 243,
        "aa_speed_p75_tokens_per_second": 364,
        "aa_speed_p95_tokens_per_second": 374,
        "aa_latency_seconds": 6.12,
        "aa_latency_first_token_seconds": 6.12,
        "aa_latency_p5_seconds": 4.81,
        "aa_latency_p25_seconds": 5.29,
        "aa_latency_p75_seconds": 7.32,
        "aa_latency_p95_seconds": 8.31,
        "aa_total_response_time_seconds": 7.83,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 25,
        "llmdex_cost_index": 99.25,
        "llmdex_speed_index": 48.7,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.02,
        "llmdex_efficiency_score": 62.22,
        "llmdex_performance_rank": 97,
        "llmdex_value_rank": 91,
        "llmdex_efficiency_rank": 23,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-1-pro-preview:preview",
        "family_id": "google/gemini-3-1-pro-preview",
        "variant_id": "google/gemini-3-1-pro-preview:preview",
        "canonical_name": "Gemini 3.1 Pro Preview",
        "source_name": "Gemini 3.1 Pro Preview",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-1-pro-preview",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-1-pro-preview",
        "source_rank": 25,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 46,
        "aa_official_coding_index": 66.5,
        "aa_omniscience_index": 33,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 23,
        "aa_terminalbench_hard": 54,
        "aa_terminalbench_v21": 74,
        "aa_tau2": 96,
        "aa_tau3_banking": 16,
        "aa_lcr": 73,
        "aa_omniscience_accuracy": 55,
        "aa_non_hallucination_rate": 50,
        "aa_hle": 45,
        "aa_gpqa": 94,
        "aa_scicode": 59,
        "aa_ifbench": 77,
        "aa_critpt": 18,
        "aa_mmmu_pro": 82,
        "aa_apex_agents": 32,
        "aa_itbench": 30,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 12,
        "aa_blended_cost_usd_per_1m": 6,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 124,
        "aa_speed_p5_tokens_per_second": 101,
        "aa_speed_p25_tokens_per_second": 108,
        "aa_speed_p75_tokens_per_second": 146,
        "aa_speed_p95_tokens_per_second": 158,
        "aa_latency_seconds": 35.43,
        "aa_latency_first_token_seconds": 35.43,
        "aa_latency_p5_seconds": 13.82,
        "aa_latency_p25_seconds": 21.75,
        "aa_latency_p75_seconds": 46.01,
        "aa_latency_p95_seconds": 96.14,
        "aa_total_response_time_seconds": 39.48,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 46,
        "llmdex_cost_index": 94,
        "llmdex_speed_index": 12.4,
        "llmdex_coverage_score": 93.8,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 53.68,
        "llmdex_efficiency_score": 23.33,
        "llmdex_performance_rank": 25,
        "llmdex_value_rank": 75,
        "llmdex_efficiency_rank": 62,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-5-flash-lite:default",
        "family_id": "google/gemini-3-5-flash-lite",
        "variant_id": "google/gemini-3-5-flash-lite:default",
        "canonical_name": "Gemini 3.5 Flash-Lite",
        "source_name": "Gemini 3.5 Flash-Lite",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-5-flash-lite",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-5-flash-lite",
        "source_rank": 55,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 36,
        "aa_official_coding_index": 47.5,
        "aa_omniscience_index": 7,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 54,
        "aa_tau2": null,
        "aa_tau3_banking": 16,
        "aa_lcr": 62,
        "aa_omniscience_accuracy": 30,
        "aa_non_hallucination_rate": 66,
        "aa_hle": 18,
        "aa_gpqa": 84,
        "aa_scicode": 41,
        "aa_ifbench": null,
        "aa_critpt": 0,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 399,
        "aa_speed_p5_tokens_per_second": 259,
        "aa_speed_p25_tokens_per_second": 341,
        "aa_speed_p75_tokens_per_second": 464,
        "aa_speed_p95_tokens_per_second": 501,
        "aa_latency_seconds": 9.4,
        "aa_latency_first_token_seconds": 9.4,
        "aa_latency_p5_seconds": 4.27,
        "aa_latency_p25_seconds": 6.45,
        "aa_latency_p75_seconds": 12.45,
        "aa_latency_p95_seconds": 42.95,
        "aa_total_response_time_seconds": 10.65,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 36,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 42.9,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.23,
        "llmdex_efficiency_score": 61.11,
        "llmdex_performance_rank": 55,
        "llmdex_value_rank": 51,
        "llmdex_efficiency_rank": 25,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-5-flash:default:gemini-3-5-flash",
        "family_id": "google/gemini-3-5-flash",
        "variant_id": "google/gemini-3-5-flash:default",
        "canonical_name": "Gemini 3.5 Flash",
        "source_name": "Gemini 3.5 Flash",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-5-flash",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-5-flash",
        "source_rank": 20,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 50,
        "aa_official_coding_index": 66,
        "aa_omniscience_index": 23,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 42,
        "aa_terminalbench_hard": 41,
        "aa_terminalbench_v21": 79,
        "aa_tau2": 95,
        "aa_tau3_banking": 25,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 52,
        "aa_non_hallucination_rate": 39,
        "aa_hle": 41,
        "aa_gpqa": 92,
        "aa_scicode": 53,
        "aa_ifbench": 76,
        "aa_critpt": 13,
        "aa_mmmu_pro": 84,
        "aa_apex_agents": 47,
        "aa_itbench": 40,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.5,
        "aa_output_cost_usd_per_1m": 9,
        "aa_blended_cost_usd_per_1m": 4.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 185,
        "aa_speed_p5_tokens_per_second": 120,
        "aa_speed_p25_tokens_per_second": 154,
        "aa_speed_p75_tokens_per_second": 209,
        "aa_speed_p95_tokens_per_second": 288,
        "aa_latency_seconds": 22.21,
        "aa_latency_first_token_seconds": 22.21,
        "aa_latency_p5_seconds": 11.41,
        "aa_latency_p25_seconds": 15.41,
        "aa_latency_p75_seconds": 83.43,
        "aa_latency_p95_seconds": 158.13,
        "aa_total_response_time_seconds": 24.91,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 50,
        "llmdex_cost_index": 95.5,
        "llmdex_speed_index": 18.5,
        "llmdex_coverage_score": 93.8,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.35,
        "llmdex_efficiency_score": 32.22,
        "llmdex_performance_rank": 20,
        "llmdex_value_rank": 34,
        "llmdex_efficiency_rank": 53,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-5-flash:default:gemini-3-5-flash-minimal",
        "family_id": "google/gemini-3-5-flash",
        "variant_id": "google/gemini-3-5-flash:default",
        "canonical_name": "Gemini 3.5 Flash (minimal)",
        "source_name": "Gemini 3.5 Flash (minimal)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-5-flash-minimal",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-5-flash-minimal",
        "source_rank": 60,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 35,
        "aa_official_coding_index": 49,
        "aa_omniscience_index": 1,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 46,
        "aa_terminalbench_v21": null,
        "aa_tau2": 59,
        "aa_tau3_banking": null,
        "aa_lcr": 53,
        "aa_omniscience_accuracy": 43,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 23,
        "aa_gpqa": 83,
        "aa_scicode": 49,
        "aa_ifbench": 47,
        "aa_critpt": 1,
        "aa_mmmu_pro": 80,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.5,
        "aa_output_cost_usd_per_1m": 9,
        "aa_blended_cost_usd_per_1m": 4.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 166,
        "aa_speed_p5_tokens_per_second": 118,
        "aa_speed_p25_tokens_per_second": 138,
        "aa_speed_p75_tokens_per_second": 187,
        "aa_speed_p95_tokens_per_second": 203,
        "aa_latency_seconds": 1.01,
        "aa_latency_first_token_seconds": 1.01,
        "aa_latency_p5_seconds": 0.71,
        "aa_latency_p25_seconds": 0.92,
        "aa_latency_p75_seconds": 1.08,
        "aa_latency_p95_seconds": 1.18,
        "aa_total_response_time_seconds": 4.02,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 35,
        "llmdex_cost_index": 95.5,
        "llmdex_speed_index": 61.55,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.46,
        "llmdex_efficiency_score": 24.44,
        "llmdex_performance_rank": 60,
        "llmdex_value_rank": 24,
        "llmdex_efficiency_rank": 60,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-5-flash:medium",
        "family_id": "google/gemini-3-5-flash",
        "variant_id": "google/gemini-3-5-flash:medium",
        "canonical_name": "Gemini 3.5 Flash (medium)",
        "source_name": "Gemini 3.5 Flash (medium)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gemini-3-5-flash-medium",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-5-flash-medium",
        "source_rank": 29,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 45,
        "aa_official_coding_index": 53,
        "aa_omniscience_index": 22,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 39,
        "aa_terminalbench_v21": null,
        "aa_tau2": 96,
        "aa_tau3_banking": null,
        "aa_lcr": 71,
        "aa_omniscience_accuracy": 51,
        "aa_non_hallucination_rate": 40,
        "aa_hle": 40,
        "aa_gpqa": 92,
        "aa_scicode": 53,
        "aa_ifbench": 75,
        "aa_critpt": 11,
        "aa_mmmu_pro": 84,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.5,
        "aa_output_cost_usd_per_1m": 9,
        "aa_blended_cost_usd_per_1m": 4.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 191,
        "aa_speed_p5_tokens_per_second": 121,
        "aa_speed_p25_tokens_per_second": 151,
        "aa_speed_p75_tokens_per_second": 216,
        "aa_speed_p95_tokens_per_second": 253,
        "aa_latency_seconds": 18.77,
        "aa_latency_first_token_seconds": 18.77,
        "aa_latency_p5_seconds": 11.88,
        "aa_latency_p25_seconds": 14.49,
        "aa_latency_p75_seconds": 42.17,
        "aa_latency_p95_seconds": 126.28,
        "aa_total_response_time_seconds": 21.39,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 45,
        "llmdex_cost_index": 95.5,
        "llmdex_speed_index": 19.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.97,
        "llmdex_efficiency_score": 29.44,
        "llmdex_performance_rank": 29,
        "llmdex_value_rank": 67,
        "llmdex_efficiency_rank": 57,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-6-flash:default",
        "family_id": "google/gemini-3-6-flash",
        "variant_id": "google/gemini-3-6-flash:default",
        "canonical_name": "Gemini 3.6 Flash",
        "source_name": "Gemini 3.6 Flash",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-6-flash",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-6-flash",
        "source_rank": 21,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 50,
        "aa_official_coding_index": 65.5,
        "aa_omniscience_index": 24,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 46,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 78,
        "aa_tau2": null,
        "aa_tau3_banking": 25,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 50,
        "aa_non_hallucination_rate": 46,
        "aa_hle": 38,
        "aa_gpqa": 93,
        "aa_scicode": 53,
        "aa_ifbench": null,
        "aa_critpt": 11,
        "aa_mmmu_pro": 83,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.5,
        "aa_output_cost_usd_per_1m": 7.5,
        "aa_blended_cost_usd_per_1m": 3.9,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 231,
        "aa_speed_p5_tokens_per_second": 160,
        "aa_speed_p25_tokens_per_second": 187,
        "aa_speed_p75_tokens_per_second": 263,
        "aa_speed_p95_tokens_per_second": 317,
        "aa_latency_seconds": 18.59,
        "aa_latency_first_token_seconds": 18.59,
        "aa_latency_p5_seconds": 9.69,
        "aa_latency_p25_seconds": 13.62,
        "aa_latency_p75_seconds": 26.86,
        "aa_latency_p95_seconds": 76.77,
        "aa_total_response_time_seconds": 20.75,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 50,
        "llmdex_cost_index": 96.1,
        "llmdex_speed_index": 23.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.45,
        "llmdex_efficiency_score": 35,
        "llmdex_performance_rank": 21,
        "llmdex_value_rank": 25,
        "llmdex_efficiency_rank": 50,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemini-3-deep-think:default",
        "family_id": "google/gemini-3-deep-think",
        "variant_id": "google/gemini-3-deep-think:default",
        "canonical_name": "Gemini 3 Deep Think",
        "source_name": "Gemini 3 Deep Think",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gemini-3-deep-think",
        "source_model_url": "https://artificialanalysis.ai/models/gemini-3-deep-think",
        "source_rank": 259,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": 26,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 6.2,
        "llmdex_confidence_factor": 0.25,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 1
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-3-270m:default",
        "family_id": "google/gemma-3-270m",
        "variant_id": "google/gemma-3-270m:default",
        "canonical_name": "Gemma 3 270M",
        "source_name": "Gemma 3 270M",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-3-270m",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-3-270m",
        "source_rank": 244,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 0,
        "aa_omniscience_index": -31,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 9,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 1,
        "aa_non_hallucination_rate": 68,
        "aa_hle": 4,
        "aa_gpqa": 22,
        "aa_scicode": 0,
        "aa_ifbench": 12,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 244,
        "llmdex_value_rank": 249,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-12b:default",
        "family_id": "google/gemma-4-12b",
        "variant_id": "google/gemma-4-12b:default",
        "canonical_name": "Gemma 4 12B",
        "source_name": "Gemma 4 12B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-4-12b",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-12b",
        "source_rank": 107,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 22,
        "aa_official_coding_index": 32.5,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 8,
        "aa_terminalbench_hard": 18,
        "aa_terminalbench_v21": 27,
        "aa_tau2": 36,
        "aa_tau3_banking": 9,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 15,
        "aa_gpqa": 75,
        "aa_scicode": 38,
        "aa_ifbench": 74,
        "aa_critpt": 0,
        "aa_mmmu_pro": 70,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.3,
        "aa_blended_cost_usd_per_1m": 0.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 110,
        "aa_speed_p5_tokens_per_second": 96,
        "aa_speed_p25_tokens_per_second": 103,
        "aa_speed_p75_tokens_per_second": 117,
        "aa_speed_p95_tokens_per_second": 127,
        "aa_latency_seconds": 2.39,
        "aa_latency_first_token_seconds": 20.52,
        "aa_latency_p5_seconds": 1.75,
        "aa_latency_p25_seconds": 2.28,
        "aa_latency_p75_seconds": 2.49,
        "aa_latency_p95_seconds": 2.65,
        "aa_total_response_time_seconds": 25.05,
        "aa_reasoning_time_seconds": 18.13,
        "llmdex_adjusted_performance": 22,
        "llmdex_cost_index": 99.82,
        "llmdex_speed_index": 49.05,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.76,
        "llmdex_efficiency_score": 83.33,
        "llmdex_performance_rank": 107,
        "llmdex_value_rank": 98,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-12b:non-reasoning",
        "family_id": "google/gemma-4-12b",
        "variant_id": "google/gemma-4-12b:non-reasoning",
        "canonical_name": "Gemma 4 12B (Non-reasoning)",
        "source_name": "Gemma 4 12B (Non-reasoning)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gemma-4-12b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-12b-non-reasoning",
        "source_rank": 158,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 13,
        "aa_official_coding_index": 30,
        "aa_omniscience_index": -53,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": null,
        "aa_tau2": 32,
        "aa_tau3_banking": null,
        "aa_lcr": 31,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 6,
        "aa_gpqa": 66,
        "aa_scicode": 30,
        "aa_ifbench": 45,
        "aa_critpt": 0,
        "aa_mmmu_pro": 62,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.3,
        "aa_blended_cost_usd_per_1m": 0.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 108,
        "aa_speed_p5_tokens_per_second": 89,
        "aa_speed_p25_tokens_per_second": 98,
        "aa_speed_p75_tokens_per_second": 115,
        "aa_speed_p95_tokens_per_second": 125,
        "aa_latency_seconds": 2.35,
        "aa_latency_first_token_seconds": 2.35,
        "aa_latency_p5_seconds": 2.18,
        "aa_latency_p25_seconds": 2.26,
        "aa_latency_p75_seconds": 2.49,
        "aa_latency_p95_seconds": 2.76,
        "aa_total_response_time_seconds": 6.98,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 13,
        "llmdex_cost_index": 99.82,
        "llmdex_speed_index": 49.05,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.26,
        "llmdex_efficiency_score": 76.67,
        "llmdex_performance_rank": 158,
        "llmdex_value_rank": 129,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-26b-a4b:default",
        "family_id": "google/gemma-4-26b-a4b",
        "variant_id": "google/gemma-4-26b-a4b:default",
        "canonical_name": "Gemma 4 26B A4B",
        "source_name": "Gemma 4 26B A4B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-4-26b-a4b",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-26b-a4b",
        "source_rank": 95,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 39.5,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 14,
        "aa_terminalbench_hard": 14,
        "aa_terminalbench_v21": 39,
        "aa_tau2": 44,
        "aa_tau3_banking": 12,
        "aa_lcr": 56,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 18,
        "aa_gpqa": 79,
        "aa_scicode": 40,
        "aa_ifbench": 72,
        "aa_critpt": 0,
        "aa_mmmu_pro": 69,
        "aa_apex_agents": null,
        "aa_itbench": 24,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.13,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.238,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": 99.76,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 65.6,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 53.66,
        "llmdex_efficiency_score": 81.67,
        "llmdex_performance_rank": 95,
        "llmdex_value_rank": 76,
        "llmdex_efficiency_rank": 10,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-26b-a4b:non-reasoning",
        "family_id": "google/gemma-4-26b-a4b",
        "variant_id": "google/gemma-4-26b-a4b:non-reasoning",
        "canonical_name": "Gemma 4 26B A4B (non-reasoning)",
        "source_name": "Gemma 4 26B A4B (non-reasoning)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gemma-4-26b-a4b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-26b-a4b-non-reasoning",
        "source_rank": 117,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 25,
        "aa_terminalbench_v21": null,
        "aa_tau2": 40,
        "aa_tau3_banking": null,
        "aa_lcr": 40,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 11,
        "aa_gpqa": 71,
        "aa_scicode": 37,
        "aa_ifbench": 45,
        "aa_critpt": 0,
        "aa_mmmu_pro": 67,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.13,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.238,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 64,
        "aa_speed_p5_tokens_per_second": 16,
        "aa_speed_p25_tokens_per_second": 29,
        "aa_speed_p75_tokens_per_second": 133,
        "aa_speed_p95_tokens_per_second": 224,
        "aa_latency_seconds": 1.17,
        "aa_latency_first_token_seconds": 1.17,
        "aa_latency_p5_seconds": 0.58,
        "aa_latency_p25_seconds": 0.93,
        "aa_latency_p75_seconds": 2.22,
        "aa_latency_p95_seconds": 9.43,
        "aa_total_response_time_seconds": 9.02,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": 99.76,
        "llmdex_speed_index": 50.55,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.04,
        "llmdex_efficiency_score": 78.89,
        "llmdex_performance_rank": 117,
        "llmdex_value_rank": 104,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-31b:default",
        "family_id": "google/gemma-4-31b",
        "variant_id": "google/gemma-4-31b:default",
        "canonical_name": "Gemma 4 31B",
        "source_name": "Gemma 4 31B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-4-31b",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-31b",
        "source_rank": 82,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 29,
        "aa_official_coding_index": 43,
        "aa_omniscience_index": -45,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 16,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": 43,
        "aa_tau2": 60,
        "aa_tau3_banking": 15,
        "aa_lcr": 62,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 23,
        "aa_gpqa": 86,
        "aa_scicode": 43,
        "aa_ifbench": 76,
        "aa_critpt": 1,
        "aa_mmmu_pro": 73,
        "aa_apex_agents": null,
        "aa_itbench": 37,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 35,
        "aa_speed_p5_tokens_per_second": 30,
        "aa_speed_p25_tokens_per_second": 34,
        "aa_speed_p75_tokens_per_second": 36,
        "aa_speed_p95_tokens_per_second": 36,
        "aa_latency_seconds": 1.03,
        "aa_latency_first_token_seconds": 50.16,
        "aa_latency_p5_seconds": 0.95,
        "aa_latency_p25_seconds": 0.99,
        "aa_latency_p75_seconds": 1.1,
        "aa_latency_p95_seconds": 1.27,
        "aa_total_response_time_seconds": 64.3,
        "aa_reasoning_time_seconds": 49.13,
        "llmdex_adjusted_performance": 29,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 48.35,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.17,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 82,
        "llmdex_value_rank": 73,
        "llmdex_efficiency_rank": 1,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-31b:non-reasoning",
        "family_id": "google/gemma-4-31b",
        "variant_id": "google/gemma-4-31b:non-reasoning",
        "canonical_name": "Gemma 4 31B (non-reasoning)",
        "source_name": "Gemma 4 31B (non-reasoning)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gemma-4-31b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning",
        "source_rank": 108,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 22,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 13,
        "aa_terminalbench_hard": 30,
        "aa_terminalbench_v21": 29,
        "aa_tau2": 65,
        "aa_tau3_banking": 8,
        "aa_lcr": 36,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 11,
        "aa_gpqa": 76,
        "aa_scicode": 41,
        "aa_ifbench": 53,
        "aa_critpt": 0,
        "aa_mmmu_pro": 70,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.244,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 66,
        "aa_speed_p5_tokens_per_second": 5,
        "aa_speed_p25_tokens_per_second": 28,
        "aa_speed_p75_tokens_per_second": 192,
        "aa_speed_p95_tokens_per_second": 2005,
        "aa_latency_seconds": 2.22,
        "aa_latency_first_token_seconds": 2.22,
        "aa_latency_p5_seconds": 0.59,
        "aa_latency_p25_seconds": 1.17,
        "aa_latency_p75_seconds": 2.97,
        "aa_latency_p95_seconds": 9.8,
        "aa_total_response_time_seconds": 9.8,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 22,
        "llmdex_cost_index": 99.76,
        "llmdex_speed_index": 45.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.03,
        "llmdex_efficiency_score": 79.44,
        "llmdex_performance_rank": 108,
        "llmdex_value_rank": 105,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-e2b:default",
        "family_id": "google/gemma-4-e2b",
        "variant_id": "google/gemma-4-e2b:default",
        "canonical_name": "Gemma 4 E2B",
        "source_name": "Gemma 4 E2B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-4-e2b",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-e2b",
        "source_rank": 179,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 10.5,
        "aa_omniscience_index": -24,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 3,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 21,
        "aa_tau3_banking": 5,
        "aa_lcr": 15,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 67,
        "aa_hle": 5,
        "aa_gpqa": 41,
        "aa_scicode": 21,
        "aa_ifbench": 36,
        "aa_critpt": 0,
        "aa_mmmu_pro": 45,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 179,
        "llmdex_value_rank": 217,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-e2b:non-reasoning",
        "family_id": "google/gemma-4-e2b",
        "variant_id": "google/gemma-4-e2b:non-reasoning",
        "canonical_name": "Gemma 4 E2B (non-reasoning)",
        "source_name": "Gemma 4 E2B (non-reasoning)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gemma-4-e2b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-e2b-non-reasoning",
        "source_rank": 211,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 20,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 22,
        "aa_tau3_banking": null,
        "aa_lcr": 15,
        "aa_omniscience_accuracy": 8,
        "aa_non_hallucination_rate": 25,
        "aa_hle": 4,
        "aa_gpqa": 41,
        "aa_scicode": 20,
        "aa_ifbench": 34,
        "aa_critpt": 0,
        "aa_mmmu_pro": 42,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 211,
        "llmdex_value_rank": 227,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-e4b:default",
        "family_id": "google/gemma-4-e4b",
        "variant_id": "google/gemma-4-e4b:default",
        "canonical_name": "Gemma 4 E4B",
        "source_name": "Gemma 4 E4B",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gemma-4-e4b",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-e4b",
        "source_rank": 167,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 13,
        "aa_omniscience_index": -20,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": 2,
        "aa_tau2": 21,
        "aa_tau3_banking": 5,
        "aa_lcr": 31,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 69,
        "aa_hle": 4,
        "aa_gpqa": 52,
        "aa_scicode": 24,
        "aa_ifbench": 41,
        "aa_critpt": 1,
        "aa_mmmu_pro": 51,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.02,
        "aa_output_cost_usd_per_1m": 0.1,
        "aa_blended_cost_usd_per_1m": 0.052,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 91,
        "aa_speed_p5_tokens_per_second": 81,
        "aa_speed_p25_tokens_per_second": 88,
        "aa_speed_p75_tokens_per_second": 94,
        "aa_speed_p95_tokens_per_second": 96,
        "aa_latency_seconds": 0.8,
        "aa_latency_first_token_seconds": 22.71,
        "aa_latency_p5_seconds": 0.7,
        "aa_latency_p25_seconds": 0.75,
        "aa_latency_p75_seconds": 0.97,
        "aa_latency_p95_seconds": 1.28,
        "aa_total_response_time_seconds": 28.18,
        "aa_reasoning_time_seconds": 21.9,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": 99.95,
        "llmdex_speed_index": 55.1,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.01,
        "llmdex_efficiency_score": 91.67,
        "llmdex_performance_rank": 167,
        "llmdex_value_rank": 127,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "google/gemma-4-e4b:non-reasoning",
        "family_id": "google/gemma-4-e4b",
        "variant_id": "google/gemma-4-e4b:non-reasoning",
        "canonical_name": "Gemma 4 E4B (non-reasoning)",
        "source_name": "Gemma 4 E4B (non-reasoning)",
        "provider": "Google",
        "creator": "Google",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gemma-4-e4b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gemma-4-e4b-non-reasoning",
        "source_rank": 188,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": -42,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": null,
        "aa_tau2": 26,
        "aa_tau3_banking": null,
        "aa_lcr": 18,
        "aa_omniscience_accuracy": 8,
        "aa_non_hallucination_rate": 46,
        "aa_hle": 5,
        "aa_gpqa": 55,
        "aa_scicode": 4,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": 51,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.02,
        "aa_output_cost_usd_per_1m": 0.1,
        "aa_blended_cost_usd_per_1m": 0.052,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 94,
        "aa_speed_p5_tokens_per_second": 78,
        "aa_speed_p25_tokens_per_second": 89,
        "aa_speed_p75_tokens_per_second": 97,
        "aa_speed_p95_tokens_per_second": 102,
        "aa_latency_seconds": 0.79,
        "aa_latency_first_token_seconds": 0.79,
        "aa_latency_p5_seconds": 0.68,
        "aa_latency_p25_seconds": 0.72,
        "aa_latency_p75_seconds": 1.04,
        "aa_latency_p95_seconds": 1.39,
        "aa_total_response_time_seconds": 6.13,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.95,
        "llmdex_speed_index": 55.45,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 45.58,
        "llmdex_efficiency_score": 87.78,
        "llmdex_performance_rank": 188,
        "llmdex_value_rank": 135,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-1b:default",
        "family_id": "ibm/granite-4-0-1b",
        "variant_id": "ibm/granite-4-0-1b:default",
        "canonical_name": "Granite 4.0 1B",
        "source_name": "Granite 4.0 1B",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-1b",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-nano-1b",
        "source_rank": 248,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 9,
        "aa_omniscience_index": -82,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 23,
        "aa_tau3_banking": null,
        "aa_lcr": 4,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 5,
        "aa_gpqa": 28,
        "aa_scicode": 9,
        "aa_ifbench": 21,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 248,
        "llmdex_value_rank": 250,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-350m:default",
        "family_id": "ibm/granite-4-0-350m",
        "variant_id": "ibm/granite-4-0-350m:default",
        "canonical_name": "Granite 4.0 350M",
        "source_name": "Granite 4.0 350M",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-350m",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-350m",
        "source_rank": 252,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 1,
        "aa_official_coding_index": 1,
        "aa_omniscience_index": -72,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 3,
        "aa_non_hallucination_rate": 22,
        "aa_hle": 6,
        "aa_gpqa": 24,
        "aa_scicode": 1,
        "aa_ifbench": 15,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 1,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 1,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 252,
        "llmdex_value_rank": 254,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-h-1b:default",
        "family_id": "ibm/granite-4-0-h-1b",
        "variant_id": "ibm/granite-4-0-h-1b:default",
        "canonical_name": "Granite 4.0 H 1B",
        "source_name": "Granite 4.0 H 1B",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-h-1b",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-h-nano-1b",
        "source_rank": 243,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 8,
        "aa_omniscience_index": -74,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 20,
        "aa_tau3_banking": null,
        "aa_lcr": 6,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 17,
        "aa_hle": 5,
        "aa_gpqa": 25,
        "aa_scicode": 8,
        "aa_ifbench": 25,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 243,
        "llmdex_value_rank": 242,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-h-350m:default",
        "family_id": "ibm/granite-4-0-h-350m",
        "variant_id": "ibm/granite-4-0-h-350m:default",
        "canonical_name": "Granite 4.0 H 350M",
        "source_name": "Granite 4.0 H 350M",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-h-350m",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-h-350m",
        "source_rank": 255,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 1,
        "aa_official_coding_index": 2,
        "aa_omniscience_index": -87,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 15,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 4,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 6,
        "aa_gpqa": 29,
        "aa_scicode": 2,
        "aa_ifbench": 17,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 1,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 1,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 255,
        "llmdex_value_rank": 255,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-h-small:default",
        "family_id": "ibm/granite-4-0-h-small",
        "variant_id": "ibm/granite-4-0-h-small:default",
        "canonical_name": "Granite 4.0 H Small",
        "source_name": "Granite 4.0 H Small",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-h-small",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-h-small",
        "source_rank": 220,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 21,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 17,
        "aa_tau3_banking": null,
        "aa_lcr": 9,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 4,
        "aa_gpqa": 42,
        "aa_scicode": 21,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.06,
        "aa_output_cost_usd_per_1m": 0.25,
        "aa_blended_cost_usd_per_1m": 0.136,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 407,
        "aa_speed_p5_tokens_per_second": 25,
        "aa_speed_p25_tokens_per_second": 267,
        "aa_speed_p75_tokens_per_second": 473,
        "aa_speed_p95_tokens_per_second": 814,
        "aa_latency_seconds": 10.22,
        "aa_latency_first_token_seconds": 10.22,
        "aa_latency_p5_seconds": 10.11,
        "aa_latency_p25_seconds": 10.2,
        "aa_latency_p75_seconds": 10.57,
        "aa_latency_p95_seconds": 11.98,
        "aa_total_response_time_seconds": 11.45,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 99.86,
        "llmdex_speed_index": 40.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 40.6,
        "llmdex_efficiency_score": 63.89,
        "llmdex_performance_rank": 220,
        "llmdex_value_rank": 168,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-0-micro:default",
        "family_id": "ibm/granite-4-0-micro",
        "variant_id": "ibm/granite-4-0-micro:default",
        "canonical_name": "Granite 4.0 Micro",
        "source_name": "Granite 4.0 Micro",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-0-micro",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-0-micro",
        "source_rank": 246,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 12,
        "aa_omniscience_index": -78,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 4,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 5,
        "aa_gpqa": 30,
        "aa_scicode": 12,
        "aa_ifbench": 22,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 246,
        "llmdex_value_rank": 251,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-1-30b:default",
        "family_id": "ibm/granite-4-1-30b",
        "variant_id": "ibm/granite-4-1-30b:default",
        "canonical_name": "Granite 4.1 30B",
        "source_name": "Granite 4.1 30B",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-1-30b",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-1-30b",
        "source_rank": 189,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 14.5,
        "aa_omniscience_index": -68,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": 3,
        "aa_tau2": 42,
        "aa_tau3_banking": 4,
        "aa_lcr": 19,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 4,
        "aa_gpqa": 48,
        "aa_scicode": 26,
        "aa_ifbench": 44,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 189,
        "llmdex_value_rank": 218,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-1-3b:default",
        "family_id": "ibm/granite-4-1-3b",
        "variant_id": "ibm/granite-4-1-3b:default",
        "canonical_name": "Granite 4.1 3B",
        "source_name": "Granite 4.1 3B",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-1-3b",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-1-3b",
        "source_rank": 225,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 6.5,
        "aa_omniscience_index": -77,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": 1,
        "aa_tau2": 20,
        "aa_tau3_banking": 1,
        "aa_lcr": 3,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 3,
        "aa_gpqa": 31,
        "aa_scicode": 12,
        "aa_ifbench": 34,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 5,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 225,
        "llmdex_value_rank": 233,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "ibm/granite-4-1-8b:default",
        "family_id": "ibm/granite-4-1-8b",
        "variant_id": "ibm/granite-4-1-8b:default",
        "canonical_name": "Granite 4.1 8B",
        "source_name": "Granite 4.1 8B",
        "provider": "IBM",
        "creator": "IBM",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "granite-4-1-8b",
        "source_model_url": "https://artificialanalysis.ai/models/granite-4-1-8b",
        "source_rank": 207,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 12.5,
        "aa_omniscience_index": -65,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 3,
        "aa_tau2": 28,
        "aa_tau3_banking": 3,
        "aa_lcr": 12,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 4,
        "aa_gpqa": 43,
        "aa_scicode": 22,
        "aa_ifbench": 39,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.05,
        "aa_output_cost_usd_per_1m": 0.1,
        "aa_blended_cost_usd_per_1m": 0.07,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 112,
        "aa_speed_p5_tokens_per_second": 69,
        "aa_speed_p25_tokens_per_second": 95,
        "aa_speed_p75_tokens_per_second": 123,
        "aa_speed_p95_tokens_per_second": 124,
        "aa_latency_seconds": 0.8,
        "aa_latency_first_token_seconds": 0.8,
        "aa_latency_p5_seconds": 0.75,
        "aa_latency_p25_seconds": 0.77,
        "aa_latency_p75_seconds": 0.83,
        "aa_latency_p95_seconds": 1.61,
        "aa_total_response_time_seconds": 5.28,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": 99.93,
        "llmdex_speed_index": 57.2,
        "llmdex_coverage_score": 81.2,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 44.92,
        "llmdex_efficiency_score": 80.56,
        "llmdex_performance_rank": 207,
        "llmdex_value_rank": 139,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inception/mercury-2:default",
        "family_id": "inception/mercury-2",
        "variant_id": "inception/mercury-2:default",
        "canonical_name": "Mercury 2",
        "source_name": "Mercury 2",
        "provider": "Inception",
        "creator": "Inception",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "mercury-2",
        "source_model_url": "https://artificialanalysis.ai/models/mercury-2",
        "source_rank": 111,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 21,
        "aa_official_coding_index": 33,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 10,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": 27,
        "aa_tau2": 71,
        "aa_tau3_banking": 10,
        "aa_lcr": 36,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 16,
        "aa_gpqa": 77,
        "aa_scicode": 39,
        "aa_ifbench": 70,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 0.75,
        "aa_blended_cost_usd_per_1m": 0.45,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 902,
        "aa_speed_p5_tokens_per_second": 643,
        "aa_speed_p25_tokens_per_second": 727,
        "aa_speed_p75_tokens_per_second": 1366,
        "aa_speed_p95_tokens_per_second": 1523,
        "aa_latency_seconds": 4.29,
        "aa_latency_first_token_seconds": 4.29,
        "aa_latency_p5_seconds": 1.71,
        "aa_latency_p25_seconds": 2.8,
        "aa_latency_p75_seconds": 7.45,
        "aa_latency_p95_seconds": 18.36,
        "aa_total_response_time_seconds": 4.84,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 21,
        "llmdex_cost_index": 99.55,
        "llmdex_speed_index": 78.55,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.07,
        "llmdex_efficiency_score": 67.22,
        "llmdex_performance_rank": 111,
        "llmdex_value_rank": 55,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inclusionai/ling-2-6-1t:default",
        "family_id": "inclusionai/ling-2-6-1t",
        "variant_id": "inclusionai/ling-2-6-1t:default",
        "canonical_name": "Ling-2.6-1T",
        "source_name": "Ling-2.6-1T",
        "provider": "InclusionAI",
        "creator": "InclusionAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ling-2-6-1t",
        "source_model_url": "https://artificialanalysis.ai/models/ling-2-6-1t",
        "source_rank": 91,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 31,
        "aa_terminalbench_v21": null,
        "aa_tau2": 90,
        "aa_tau3_banking": null,
        "aa_lcr": 35,
        "aa_omniscience_accuracy": 21,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 8,
        "aa_gpqa": 75,
        "aa_scicode": 37,
        "aa_ifbench": 57,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 53.31,
        "llmdex_efficiency_score": 53.89,
        "llmdex_performance_rank": 91,
        "llmdex_value_rank": 80,
        "llmdex_efficiency_rank": 29,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inclusionai/ling-2-6-flash:default",
        "family_id": "inclusionai/ling-2-6-flash",
        "variant_id": "inclusionai/ling-2-6-flash:default",
        "canonical_name": "Ling 2.6 Flash",
        "source_name": "Ling 2.6 Flash",
        "provider": "InclusionAI",
        "creator": "InclusionAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ling-2-6-flash",
        "source_model_url": "https://artificialanalysis.ai/models/ling-2-6-flash",
        "source_rank": 154,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 25.5,
        "aa_omniscience_index": -66,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 3,
        "aa_terminalbench_hard": 21,
        "aa_terminalbench_v21": 24,
        "aa_tau2": 86,
        "aa_tau3_banking": 3,
        "aa_lcr": 25,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 6,
        "aa_gpqa": 59,
        "aa_scicode": 27,
        "aa_ifbench": 57,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.3,
        "aa_blended_cost_usd_per_1m": 0.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 168,
        "aa_speed_p5_tokens_per_second": 90,
        "aa_speed_p25_tokens_per_second": 142,
        "aa_speed_p75_tokens_per_second": 185,
        "aa_speed_p95_tokens_per_second": 211,
        "aa_latency_seconds": 1.16,
        "aa_latency_first_token_seconds": 1.16,
        "aa_latency_p5_seconds": 1.06,
        "aa_latency_p25_seconds": 1.12,
        "aa_latency_p75_seconds": 1.22,
        "aa_latency_p95_seconds": 2.57,
        "aa_total_response_time_seconds": 4.13,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 99.82,
        "llmdex_speed_index": 61,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 49.15,
        "llmdex_efficiency_score": 78.33,
        "llmdex_performance_rank": 154,
        "llmdex_value_rank": 111,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inclusionai/ling-mini-2-0:default",
        "family_id": "inclusionai/ling-mini-2-0",
        "variant_id": "inclusionai/ling-mini-2-0:default",
        "canonical_name": "Ling-mini-2.0",
        "source_name": "Ling-mini-2.0",
        "provider": "InclusionAI",
        "creator": "InclusionAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ling-mini-2-0",
        "source_model_url": "https://artificialanalysis.ai/models/ling-mini-2-0",
        "source_rank": 233,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 14,
        "aa_omniscience_index": -79,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 5,
        "aa_gpqa": 56,
        "aa_scicode": 14,
        "aa_ifbench": 24,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 4,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 233,
        "llmdex_value_rank": 236,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inclusionai/ring-2-6-1t:default",
        "family_id": "inclusionai/ring-2-6-1t",
        "variant_id": "inclusionai/ring-2-6-1t:default",
        "canonical_name": "Ring-2.6-1T",
        "source_name": "Ring-2.6-1T",
        "provider": "InclusionAI",
        "creator": "InclusionAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ring-2-6-1t",
        "source_model_url": "https://artificialanalysis.ai/models/ring-2-6-1t",
        "source_rank": 76,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 31,
        "aa_official_coding_index": 42.5,
        "aa_omniscience_index": -38,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 21,
        "aa_terminalbench_hard": 29,
        "aa_terminalbench_v21": 43,
        "aa_tau2": 92,
        "aa_tau3_banking": 14,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 18,
        "aa_gpqa": 86,
        "aa_scicode": 42,
        "aa_ifbench": 45,
        "aa_critpt": 4,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 121,
        "aa_speed_p5_tokens_per_second": 86,
        "aa_speed_p25_tokens_per_second": 114,
        "aa_speed_p75_tokens_per_second": 137,
        "aa_speed_p95_tokens_per_second": 143,
        "aa_latency_seconds": 3.31,
        "aa_latency_first_token_seconds": 19.88,
        "aa_latency_p5_seconds": 2.88,
        "aa_latency_p25_seconds": 2.99,
        "aa_latency_p75_seconds": 3.72,
        "aa_latency_p95_seconds": 6.51,
        "aa_total_response_time_seconds": 24.02,
        "aa_reasoning_time_seconds": 16.57,
        "llmdex_adjusted_performance": 31,
        "llmdex_cost_index": 98.82,
        "llmdex_speed_index": 45.55,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.26,
        "llmdex_efficiency_score": 57.22,
        "llmdex_performance_rank": 76,
        "llmdex_value_rank": 71,
        "llmdex_efficiency_rank": 27,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "inclusionai/ring-flash-2-0:default",
        "family_id": "inclusionai/ring-flash-2-0",
        "variant_id": "inclusionai/ring-flash-2-0:default",
        "canonical_name": "Ring-flash-2.0",
        "source_name": "Ring-flash-2.0",
        "provider": "InclusionAI",
        "creator": "InclusionAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ring-flash-2-0",
        "source_model_url": "https://artificialanalysis.ai/models/ring-flash-2-0",
        "source_rank": 198,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 8,
        "aa_official_coding_index": 17,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 21,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 9,
        "aa_gpqa": 73,
        "aa_scicode": 17,
        "aa_ifbench": 43,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.57,
        "aa_blended_cost_usd_per_1m": 0.312,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 8,
        "llmdex_cost_index": 99.69,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 42.38,
        "llmdex_efficiency_score": 56.11,
        "llmdex_performance_rank": 198,
        "llmdex_value_rank": 154,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kimi/kimi-k2-6:non-reasoning",
        "family_id": "kimi/kimi-k2-6",
        "variant_id": "kimi/kimi-k2-6:non-reasoning",
        "canonical_name": "Kimi K2.6 (non-reasoning)",
        "source_name": "Kimi K2.6 (non-reasoning)",
        "provider": "Kimi",
        "creator": "Kimi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "kimi-k2-6-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning",
        "source_rank": 61,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 35,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -10,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 38,
        "aa_terminalbench_v21": null,
        "aa_tau2": 94,
        "aa_tau3_banking": null,
        "aa_lcr": 58,
        "aa_omniscience_accuracy": 23,
        "aa_non_hallucination_rate": 57,
        "aa_hle": 18,
        "aa_gpqa": 79,
        "aa_scicode": 39,
        "aa_ifbench": 44,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.95,
        "aa_output_cost_usd_per_1m": 4,
        "aa_blended_cost_usd_per_1m": 2.17,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 36,
        "aa_speed_p5_tokens_per_second": 26,
        "aa_speed_p25_tokens_per_second": 31,
        "aa_speed_p75_tokens_per_second": 45,
        "aa_speed_p95_tokens_per_second": 62,
        "aa_latency_seconds": 2.98,
        "aa_latency_first_token_seconds": 2.98,
        "aa_latency_p5_seconds": 2.04,
        "aa_latency_p25_seconds": 2.18,
        "aa_latency_p75_seconds": 3.29,
        "aa_latency_p95_seconds": 4.84,
        "aa_total_response_time_seconds": 16.88,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 35,
        "llmdex_cost_index": 97.83,
        "llmdex_speed_index": 38.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.59,
        "llmdex_efficiency_score": 42.78,
        "llmdex_performance_rank": 61,
        "llmdex_value_rank": 69,
        "llmdex_efficiency_rank": 43,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kimi/kimi-k2-7-code:default",
        "family_id": "kimi/kimi-k2-7-code",
        "variant_id": "kimi/kimi-k2-7-code:default",
        "canonical_name": "Kimi K2.7 Code",
        "source_name": "Kimi K2.7 Code",
        "provider": "Kimi",
        "creator": "Kimi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "kimi-k2-7-code",
        "source_model_url": "https://artificialanalysis.ai/models/kimi-k2-7-code",
        "source_rank": 38,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 42,
        "aa_official_coding_index": 57,
        "aa_omniscience_index": -11,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 34,
        "aa_terminalbench_hard": 45,
        "aa_terminalbench_v21": 67,
        "aa_tau2": 90,
        "aa_tau3_banking": 18,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 39,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 33,
        "aa_gpqa": 90,
        "aa_scicode": 47,
        "aa_ifbench": 63,
        "aa_critpt": 10,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.95,
        "aa_output_cost_usd_per_1m": 4,
        "aa_blended_cost_usd_per_1m": 2.17,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 51,
        "aa_speed_p5_tokens_per_second": 37,
        "aa_speed_p25_tokens_per_second": 43,
        "aa_speed_p75_tokens_per_second": 54,
        "aa_speed_p95_tokens_per_second": 95,
        "aa_latency_seconds": 2.82,
        "aa_latency_first_token_seconds": 46.3,
        "aa_latency_p5_seconds": 1.55,
        "aa_latency_p25_seconds": 2.66,
        "aa_latency_p75_seconds": 3.03,
        "aa_latency_p95_seconds": 3.39,
        "aa_total_response_time_seconds": 56.06,
        "aa_reasoning_time_seconds": 43.48,
        "llmdex_adjusted_performance": 42,
        "llmdex_cost_index": 97.83,
        "llmdex_speed_index": 41,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.55,
        "llmdex_efficiency_score": 48.89,
        "llmdex_performance_rank": 38,
        "llmdex_value_rank": 22,
        "llmdex_efficiency_rank": 36,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kimi/kimi-k3:default",
        "family_id": "kimi/kimi-k3",
        "variant_id": "kimi/kimi-k3:default",
        "canonical_name": "Kimi K3",
        "source_name": "Kimi K3",
        "provider": "Kimi",
        "creator": "Kimi",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "kimi-k3",
        "source_model_url": "https://artificialanalysis.ai/models/kimi-k3",
        "source_rank": 7,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 57,
        "aa_official_coding_index": 72,
        "aa_omniscience_index": 18,
        "aa_context_window_tokens": 1050000,
        "aa_gdpval": 59,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 85,
        "aa_tau2": null,
        "aa_tau3_banking": 33,
        "aa_lcr": 75,
        "aa_omniscience_accuracy": 46,
        "aa_non_hallucination_rate": 49,
        "aa_hle": 44,
        "aa_gpqa": 94,
        "aa_scicode": 59,
        "aa_ifbench": null,
        "aa_critpt": 23,
        "aa_mmmu_pro": 81,
        "aa_apex_agents": 41,
        "aa_itbench": 48,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 3,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 32,
        "aa_speed_p5_tokens_per_second": 15,
        "aa_speed_p25_tokens_per_second": 28,
        "aa_speed_p75_tokens_per_second": 36,
        "aa_speed_p95_tokens_per_second": 42,
        "aa_latency_seconds": 189.77,
        "aa_latency_first_token_seconds": 252.11,
        "aa_latency_p5_seconds": 130.21,
        "aa_latency_p25_seconds": 158.9,
        "aa_latency_p75_seconds": 268.19,
        "aa_latency_p95_seconds": 562.16,
        "aa_total_response_time_seconds": 267.7,
        "aa_reasoning_time_seconds": 62.34,
        "llmdex_adjusted_performance": 57,
        "llmdex_cost_index": 92.2,
        "llmdex_speed_index": 3.2,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.8,
        "llmdex_efficiency_score": 22.22,
        "llmdex_performance_rank": 7,
        "llmdex_value_rank": 42,
        "llmdex_efficiency_rank": 64,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kimi/kimi-linear-48b-a3b-instruct:default",
        "family_id": "kimi/kimi-linear-48b-a3b-instruct",
        "variant_id": "kimi/kimi-linear-48b-a3b-instruct:default",
        "canonical_name": "Kimi Linear 48B A3B Instruct",
        "source_name": "Kimi Linear 48B A3B Instruct",
        "provider": "Kimi",
        "creator": "Kimi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "kimi-linear-48b-a3b-instruct",
        "source_model_url": "https://artificialanalysis.ai/models/kimi-linear-48b-a3b-instruct",
        "source_rank": 195,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 20,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 26,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 3,
        "aa_gpqa": 41,
        "aa_scicode": 20,
        "aa_ifbench": 28,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 31.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 195,
        "llmdex_value_rank": 220,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "korea-telecom/mi-dm-k-2-5-pro-preview:preview",
        "family_id": "korea-telecom/mi-dm-k-2-5-pro-preview",
        "variant_id": "korea-telecom/mi-dm-k-2-5-pro-preview:preview",
        "canonical_name": "Mi:dm K 2.5 Pro Preview",
        "source_name": "Mi:dm K 2.5 Pro Preview",
        "provider": "Korea Telecom",
        "creator": "Korea Telecom",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "mi-dm-k-2-5-pro-preview",
        "source_model_url": "https://artificialanalysis.ai/models/midm-250-pro-rsnsft",
        "source_rank": 261,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": 30,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 3,
        "aa_terminalbench_v21": null,
        "aa_tau2": 49,
        "aa_tau3_banking": null,
        "aa_lcr": 11,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 7,
        "aa_hle": 9,
        "aa_gpqa": 72,
        "aa_scicode": 30,
        "aa_ifbench": 46,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 40.6,
        "llmdex_confidence_factor": 0.25,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 1
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "korea-telecom/mi-dm-k-2-5-pro:default",
        "family_id": "korea-telecom/mi-dm-k-2-5-pro",
        "variant_id": "korea-telecom/mi-dm-k-2-5-pro:default",
        "canonical_name": "Mi:dm K 2.5 Pro",
        "source_name": "Mi:dm K 2.5 Pro",
        "provider": "Korea Telecom",
        "creator": "Korea Telecom",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "mi-dm-k-2-5-pro",
        "source_model_url": "https://artificialanalysis.ai/models/mi-dm-k-2-5-pro-dec28",
        "source_rank": 139,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 16,
        "aa_official_coding_index": 33,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 87,
        "aa_tau3_banking": null,
        "aa_lcr": 9,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 8,
        "aa_gpqa": 70,
        "aa_scicode": 33,
        "aa_ifbench": 49,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 16,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 16,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 139,
        "llmdex_value_rank": 203,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kwaikat/kat-coder-pro-v1:default",
        "family_id": "kwaikat/kat-coder-pro-v1",
        "variant_id": "kwaikat/kat-coder-pro-v1:default",
        "canonical_name": "KAT-Coder-Pro V1",
        "source_name": "KAT-Coder-Pro V1",
        "provider": "KwaiKAT",
        "creator": "KwaiKAT",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "kat-coder-pro-v1",
        "source_model_url": "https://artificialanalysis.ai/models/kat-coder-pro-v1",
        "source_rank": 86,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 28,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -37,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 20,
        "aa_terminalbench_hard": 9,
        "aa_terminalbench_v21": null,
        "aa_tau2": 89,
        "aa_tau3_banking": null,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 33,
        "aa_hle": 33,
        "aa_gpqa": 76,
        "aa_scicode": 37,
        "aa_ifbench": 68,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 28,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 28,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 86,
        "llmdex_value_rank": 189,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "kwaikat/kat-coder-pro-v2:default",
        "family_id": "kwaikat/kat-coder-pro-v2",
        "variant_id": "kwaikat/kat-coder-pro-v2:default",
        "canonical_name": "KAT-Coder-Pro V2",
        "source_name": "KAT-Coder-Pro V2",
        "provider": "KwaiKAT",
        "creator": "KwaiKAT",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "kat-coder-pro-v2",
        "source_model_url": "https://artificialanalysis.ai/models/kat-coder-pro-v2",
        "source_rank": 65,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 54,
        "aa_omniscience_index": -22,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 20,
        "aa_terminalbench_hard": 49,
        "aa_terminalbench_v21": 70,
        "aa_tau2": 89,
        "aa_tau3_banking": 6,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 44,
        "aa_hle": 16,
        "aa_gpqa": 85,
        "aa_scicode": 38,
        "aa_ifbench": 67,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 1.2,
        "aa_blended_cost_usd_per_1m": 0.66,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 100,
        "aa_speed_p5_tokens_per_second": 73,
        "aa_speed_p25_tokens_per_second": 94,
        "aa_speed_p75_tokens_per_second": 108,
        "aa_speed_p95_tokens_per_second": 120,
        "aa_latency_seconds": 1.62,
        "aa_latency_first_token_seconds": 1.62,
        "aa_latency_p5_seconds": 1.15,
        "aa_latency_p25_seconds": 1.23,
        "aa_latency_p75_seconds": 1.92,
        "aa_latency_p95_seconds": 2.65,
        "aa_total_response_time_seconds": 6.61,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 99.34,
        "llmdex_speed_index": 51.9,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.18,
        "llmdex_efficiency_score": 68.89,
        "llmdex_performance_rank": 65,
        "llmdex_value_rank": 37,
        "llmdex_efficiency_rank": 18,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-0-1-2b:default",
        "family_id": "lg-ai-research/exaone-4-0-1-2b",
        "variant_id": "lg-ai-research/exaone-4-0-1-2b:default",
        "canonical_name": "Exaone 4.0 1.2B",
        "source_name": "Exaone 4.0 1.2B",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "exaone-4-0-1-2b",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-0-1-2b",
        "source_rank": 238,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 7,
        "aa_omniscience_index": -83,
        "aa_context_window_tokens": 64000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 20,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 6,
        "aa_gpqa": 42,
        "aa_scicode": 7,
        "aa_ifbench": 25,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 238,
        "llmdex_value_rank": 240,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-0-1-2b:reasoning",
        "family_id": "lg-ai-research/exaone-4-0-1-2b",
        "variant_id": "lg-ai-research/exaone-4-0-1-2b:reasoning",
        "canonical_name": "Exaone 4.0 1.2B (reasoning)",
        "source_name": "Exaone 4.0 1.2B (reasoning)",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "exaone-4-0-1-2b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-0-1-2b-reasoning",
        "source_rank": 236,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 9,
        "aa_omniscience_index": -82,
        "aa_context_window_tokens": 64000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 16,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 6,
        "aa_gpqa": 52,
        "aa_scicode": 9,
        "aa_ifbench": 23,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 236,
        "llmdex_value_rank": 241,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-0-32b:default",
        "family_id": "lg-ai-research/exaone-4-0-32b",
        "variant_id": "lg-ai-research/exaone-4-0-32b:default",
        "canonical_name": "EXAONE 4.0 32B",
        "source_name": "EXAONE 4.0 32B",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "exaone-4-0-32b",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-0-32b",
        "source_rank": 215,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 4,
        "aa_tau3_banking": null,
        "aa_lcr": 8,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 5,
        "aa_gpqa": 63,
        "aa_scicode": 25,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 215,
        "llmdex_value_rank": 226,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-0-32b:reasoning",
        "family_id": "lg-ai-research/exaone-4-0-32b",
        "variant_id": "lg-ai-research/exaone-4-0-32b:reasoning",
        "canonical_name": "EXAONE 4.0 32B (reasoning)",
        "source_name": "EXAONE 4.0 32B (reasoning)",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "exaone-4-0-32b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-0-32b-reasoning",
        "source_rank": 173,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 11,
        "aa_official_coding_index": 34,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 17,
        "aa_tau3_banking": null,
        "aa_lcr": 14,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 14,
        "aa_hle": 11,
        "aa_gpqa": 74,
        "aa_scicode": 34,
        "aa_ifbench": 36,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 11,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 11,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 173,
        "llmdex_value_rank": 214,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-5-33b:default",
        "family_id": "lg-ai-research/exaone-4-5-33b",
        "variant_id": "lg-ai-research/exaone-4-5-33b:default",
        "canonical_name": "EXAONE 4.5 33B",
        "source_name": "EXAONE 4.5 33B",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "exaone-4-5-33b",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-5-33b",
        "source_rank": 116,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 24.5,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 9,
        "aa_terminalbench_hard": 20,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 78,
        "aa_tau3_banking": 11,
        "aa_lcr": 49,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 12,
        "aa_gpqa": 79,
        "aa_scicode": 28,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": 67,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 20,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 116,
        "llmdex_value_rank": 194,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/exaone-4-5-33b:non-reasoning",
        "family_id": "lg-ai-research/exaone-4-5-33b",
        "variant_id": "lg-ai-research/exaone-4-5-33b:non-reasoning",
        "canonical_name": "EXAONE 4.5 33B (non-reasoning)",
        "source_name": "EXAONE 4.5 33B (non-reasoning)",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "exaone-4-5-33b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/exaone-4-5-33b-non-reasoning",
        "source_rank": 257,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 3.1,
        "llmdex_confidence_factor": 0,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 0
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/k-exaone:default",
        "family_id": "lg-ai-research/k-exaone",
        "variant_id": "lg-ai-research/k-exaone:default",
        "canonical_name": "K-EXAONE",
        "source_name": "K-EXAONE",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "k-exaone",
        "source_model_url": "https://artificialanalysis.ai/models/k-exaone",
        "source_rank": 105,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 22,
        "aa_official_coding_index": 33,
        "aa_omniscience_index": -58,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 5,
        "aa_terminalbench_hard": 23,
        "aa_terminalbench_v21": 30,
        "aa_tau2": 74,
        "aa_tau3_banking": 14,
        "aa_lcr": 56,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 13,
        "aa_gpqa": 78,
        "aa_scicode": 36,
        "aa_ifbench": 65,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 22,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 22,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 105,
        "llmdex_value_rank": 193,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "lg-ai-research/k-exaone:non-reasoning",
        "family_id": "lg-ai-research/k-exaone",
        "variant_id": "lg-ai-research/k-exaone:non-reasoning",
        "canonical_name": "K-EXAONE (non-reasoning)",
        "source_name": "K-EXAONE (non-reasoning)",
        "provider": "LG AI Research",
        "creator": "LG AI Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "k-exaone-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/k-exaone-non-reasoning",
        "source_rank": 136,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 27,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": null,
        "aa_tau2": 59,
        "aa_tau3_banking": null,
        "aa_lcr": 47,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 5,
        "aa_gpqa": 69,
        "aa_scicode": 27,
        "aa_ifbench": 40,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 17,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 136,
        "llmdex_value_rank": 199,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-2-6b:default",
        "family_id": "liquid-ai/lfm2-2-6b",
        "variant_id": "liquid-ai/lfm2-2-6b:default",
        "canonical_name": "LFM2 2.6B",
        "source_name": "LFM2 2.6B",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-2-6b",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-2-6b",
        "source_rank": 241,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 3,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 40,
        "aa_hle": 5,
        "aa_gpqa": 32,
        "aa_scicode": 3,
        "aa_ifbench": 26,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 241,
        "llmdex_value_rank": 244,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-24b-a2b:default",
        "family_id": "liquid-ai/lfm2-24b-a2b",
        "variant_id": "liquid-ai/lfm2-24b-a2b:default",
        "canonical_name": "LFM2 24B A2B",
        "source_name": "LFM2 24B A2B",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-24b-a2b",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-24b-a2b",
        "source_rank": 222,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 11,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 11,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 30,
        "aa_hle": 4,
        "aa_gpqa": 47,
        "aa_scicode": 11,
        "aa_ifbench": 46,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 5,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 222,
        "llmdex_value_rank": 234,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-5-1-2b-instruct:default",
        "family_id": "liquid-ai/lfm2-5-1-2b-instruct",
        "variant_id": "liquid-ai/lfm2-5-1-2b-instruct:default",
        "canonical_name": "LFM2.5-1.2B-Instruct",
        "source_name": "LFM2.5-1.2B-Instruct",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-5-1-2b-instruct",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-5-1-2b-instruct",
        "source_rank": 242,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 2,
        "aa_omniscience_index": -74,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 11,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 7,
        "aa_gpqa": 29,
        "aa_scicode": 2,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 242,
        "llmdex_value_rank": 245,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-5-1-2b:thinking",
        "family_id": "liquid-ai/lfm2-5-1-2b",
        "variant_id": "liquid-ai/lfm2-5-1-2b:thinking",
        "canonical_name": "LFM2.5-1.2B-Thinking",
        "source_name": "LFM2.5-1.2B-Thinking",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-5-1-2b-thinking",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-5-1-2b-thinking",
        "source_rank": 239,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": -84,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 20,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 6,
        "aa_gpqa": 34,
        "aa_scicode": 4,
        "aa_ifbench": 42,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 3,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 239,
        "llmdex_value_rank": 246,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-5-8b-a1b:default",
        "family_id": "liquid-ai/lfm2-5-8b-a1b",
        "variant_id": "liquid-ai/lfm2-5-8b-a1b:default",
        "canonical_name": "LFM2.5-8B-A1B",
        "source_name": "LFM2.5-8B-A1B",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-5-8b-a1b",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-5-8b-a1b",
        "source_rank": 197,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 8,
        "aa_official_coding_index": 8,
        "aa_omniscience_index": -33,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 16,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 53,
        "aa_hle": 7,
        "aa_gpqa": 47,
        "aa_scicode": 8,
        "aa_ifbench": 53,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 334,
        "aa_speed_p5_tokens_per_second": 289,
        "aa_speed_p25_tokens_per_second": 329,
        "aa_speed_p75_tokens_per_second": 341,
        "aa_speed_p95_tokens_per_second": 356,
        "aa_latency_seconds": 2.15,
        "aa_latency_first_token_seconds": 8.14,
        "aa_latency_p5_seconds": 0.74,
        "aa_latency_p25_seconds": 1.21,
        "aa_latency_p75_seconds": 7.77,
        "aa_latency_p95_seconds": 12.88,
        "aa_total_response_time_seconds": 9.63,
        "aa_reasoning_time_seconds": 5.98,
        "llmdex_adjusted_performance": 8,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 72.65,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 48.53,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 197,
        "llmdex_value_rank": 113,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-5-vl-1-6b:default",
        "family_id": "liquid-ai/lfm2-5-vl-1-6b",
        "variant_id": "liquid-ai/lfm2-5-vl-1-6b:default",
        "canonical_name": "LFM2.5-VL-1.6B",
        "source_name": "LFM2.5-VL-1.6B",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-5-vl-1-6b",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-5-vl-1-6b",
        "source_rank": 251,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 1,
        "aa_official_coding_index": 3,
        "aa_omniscience_index": -84,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 8,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 5,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 5,
        "aa_gpqa": 29,
        "aa_scicode": 3,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": 27,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 369,
        "aa_speed_p5_tokens_per_second": 285,
        "aa_speed_p25_tokens_per_second": 335,
        "aa_speed_p75_tokens_per_second": 407,
        "aa_speed_p95_tokens_per_second": 559,
        "aa_latency_seconds": 11.9,
        "aa_latency_first_token_seconds": 11.9,
        "aa_latency_p5_seconds": 0.61,
        "aa_latency_p25_seconds": 1.98,
        "aa_latency_p75_seconds": 12.27,
        "aa_latency_p95_seconds": 13.92,
        "aa_total_response_time_seconds": 13.25,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 1,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 36.9,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 37.88,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 251,
        "llmdex_value_rank": 181,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "liquid-ai/lfm2-8b-a1b:default",
        "family_id": "liquid-ai/lfm2-8b-a1b",
        "variant_id": "liquid-ai/lfm2-8b-a1b:default",
        "canonical_name": "LFM2 8B A1B",
        "source_name": "LFM2 8B A1B",
        "provider": "Liquid AI",
        "creator": "Liquid AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "lfm2-8b-a1b",
        "source_model_url": "https://artificialanalysis.ai/models/lfm2-8b-a1b",
        "source_rank": 250,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 7,
        "aa_omniscience_index": -75,
        "aa_context_window_tokens": 32800,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 11,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 7,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 5,
        "aa_gpqa": 34,
        "aa_scicode": 7,
        "aa_ifbench": 26,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 250,
        "llmdex_value_rank": 252,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "longcat/longcat-2-0:default",
        "family_id": "longcat/longcat-2-0",
        "variant_id": "longcat/longcat-2-0:default",
        "canonical_name": "LongCat 2.0",
        "source_name": "LongCat 2.0",
        "provider": "LongCat",
        "creator": "LongCat",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "longcat-2-0",
        "source_model_url": "https://artificialanalysis.ai/models/longcat-2-0",
        "source_rank": 68,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 33,
        "aa_official_coding_index": 42.5,
        "aa_omniscience_index": -23,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 26,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 50,
        "aa_tau2": null,
        "aa_tau3_banking": 13,
        "aa_lcr": 58,
        "aa_omniscience_accuracy": 30,
        "aa_non_hallucination_rate": 25,
        "aa_hle": 32,
        "aa_gpqa": 78,
        "aa_scicode": 35,
        "aa_ifbench": null,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 33,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 33,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 68,
        "llmdex_value_rank": 186,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "longcat/longcat-flash-lite:default",
        "family_id": "longcat/longcat-flash-lite",
        "variant_id": "longcat/longcat-flash-lite:default",
        "canonical_name": "LongCat Flash Lite",
        "source_name": "LongCat Flash Lite",
        "provider": "LongCat",
        "creator": "LongCat",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "longcat-flash-lite",
        "source_model_url": "https://artificialanalysis.ai/models/longcat-flash-lite",
        "source_rank": 134,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -70,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": null,
        "aa_tau2": 80,
        "aa_tau3_banking": null,
        "aa_lcr": 26,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 4,
        "aa_hle": 6,
        "aa_gpqa": 64,
        "aa_scicode": 28,
        "aa_ifbench": 43,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 17,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 134,
        "llmdex_value_rank": 201,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mbzuai-institute-of-foundation-models/k2-think-v2:default",
        "family_id": "mbzuai-institute-of-foundation-models/k2-think-v2",
        "variant_id": "mbzuai-institute-of-foundation-models/k2-think-v2:default",
        "canonical_name": "K2 Think V2",
        "source_name": "K2 Think V2",
        "provider": "MBZUAI Institute of Foundation Models",
        "creator": "MBZUAI Institute of Foundation Models",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "k2-think-v2",
        "source_model_url": "https://artificialanalysis.ai/models/k2-think-v2",
        "source_rank": 133,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": -34,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": 15,
        "aa_tau2": 25,
        "aa_tau3_banking": 5,
        "aa_lcr": 53,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 41,
        "aa_hle": 9,
        "aa_gpqa": 71,
        "aa_scicode": 33,
        "aa_ifbench": 63,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 17,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 133,
        "llmdex_value_rank": 200,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mbzuai-institute-of-foundation-models/k2-v2:high",
        "family_id": "mbzuai-institute-of-foundation-models/k2-v2",
        "variant_id": "mbzuai-institute-of-foundation-models/k2-v2:high",
        "canonical_name": "K2-V2 (high)",
        "source_name": "K2-V2 (high)",
        "provider": "MBZUAI Institute of Foundation Models",
        "creator": "MBZUAI Institute of Foundation Models",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "k2-v2-high",
        "source_model_url": "https://artificialanalysis.ai/models/k2-v2",
        "source_rank": 151,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 29,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 512000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 10,
        "aa_terminalbench_v21": null,
        "aa_tau2": 28,
        "aa_tau3_banking": null,
        "aa_lcr": 33,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 10,
        "aa_gpqa": 68,
        "aa_scicode": 29,
        "aa_ifbench": 60,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 14,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 151,
        "llmdex_value_rank": 205,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mbzuai-institute-of-foundation-models/k2-v2:low",
        "family_id": "mbzuai-institute-of-foundation-models/k2-v2",
        "variant_id": "mbzuai-institute-of-foundation-models/k2-v2:low",
        "canonical_name": "K2-V2 (low)",
        "source_name": "K2-V2 (low)",
        "provider": "MBZUAI Institute of Foundation Models",
        "creator": "MBZUAI Institute of Foundation Models",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "k2-v2-low",
        "source_model_url": "https://artificialanalysis.ai/models/k2-v2-low",
        "source_rank": 194,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 22,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 512000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 21,
        "aa_tau3_banking": null,
        "aa_lcr": 19,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 24,
        "aa_hle": 4,
        "aa_gpqa": 54,
        "aa_scicode": 22,
        "aa_ifbench": 41,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 194,
        "llmdex_value_rank": 219,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mbzuai-institute-of-foundation-models/k2-v2:medium",
        "family_id": "mbzuai-institute-of-foundation-models/k2-v2",
        "variant_id": "mbzuai-institute-of-foundation-models/k2-v2:medium",
        "canonical_name": "K2-V2 (medium)",
        "source_name": "K2-V2 (medium)",
        "provider": "MBZUAI Institute of Foundation Models",
        "creator": "MBZUAI Institute of Foundation Models",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "k2-v2-medium",
        "source_model_url": "https://artificialanalysis.ai/models/k2-v2-medium",
        "source_rank": 161,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -50,
        "aa_context_window_tokens": 512000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": null,
        "aa_tau2": 25,
        "aa_tau3_banking": null,
        "aa_lcr": 28,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 4,
        "aa_gpqa": 60,
        "aa_scicode": 25,
        "aa_ifbench": 55,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 12,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 161,
        "llmdex_value_rank": 210,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-3-1-405b:default",
        "family_id": "meta/llama-3-1-405b",
        "variant_id": "meta/llama-3-1-405b:default",
        "canonical_name": "Llama 3.1 405B",
        "source_name": "Llama 3.1 405B",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-3-1-405b",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-1-instruct-405b",
        "source_rank": 196,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 30,
        "aa_omniscience_index": -17,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": null,
        "aa_tau2": 19,
        "aa_tau3_banking": null,
        "aa_lcr": 24,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 49,
        "aa_hle": 4,
        "aa_gpqa": 52,
        "aa_scicode": 30,
        "aa_ifbench": 39,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 10,
        "aa_blended_cost_usd_per_1m": 5.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 94.5,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 41.06,
        "llmdex_efficiency_score": 2.22,
        "llmdex_performance_rank": 196,
        "llmdex_value_rank": 165,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-3-2-11b-vision:default",
        "family_id": "meta/llama-3-2-11b-vision",
        "variant_id": "meta/llama-3-2-11b-vision:default",
        "canonical_name": "Llama 3.2 11B (Vision)",
        "source_name": "Llama 3.2 11B (Vision)",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-3-2-11b-vision",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-2-instruct-11b-vision",
        "source_rank": 234,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 3,
        "aa_official_coding_index": 11,
        "aa_omniscience_index": -63,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 15,
        "aa_tau3_banking": null,
        "aa_lcr": 12,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 5,
        "aa_gpqa": 22,
        "aa_scicode": 11,
        "aa_ifbench": 30,
        "aa_critpt": 0,
        "aa_mmmu_pro": 29,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.36,
        "aa_output_cost_usd_per_1m": 0.36,
        "aa_blended_cost_usd_per_1m": 0.36,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 8,
        "aa_speed_p5_tokens_per_second": 4,
        "aa_speed_p25_tokens_per_second": 6,
        "aa_speed_p75_tokens_per_second": 14,
        "aa_speed_p95_tokens_per_second": 20,
        "aa_latency_seconds": 2.59,
        "aa_latency_first_token_seconds": 2.59,
        "aa_latency_p5_seconds": 0.96,
        "aa_latency_p25_seconds": 2.08,
        "aa_latency_p75_seconds": 3.54,
        "aa_latency_p95_seconds": 16.98,
        "aa_total_response_time_seconds": 68.73,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 3,
        "llmdex_cost_index": 99.64,
        "llmdex_speed_index": 37.85,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 38.96,
        "llmdex_efficiency_score": 26.11,
        "llmdex_performance_rank": 234,
        "llmdex_value_rank": 176,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-3-2-90b-vision:default",
        "family_id": "meta/llama-3-2-90b-vision",
        "variant_id": "meta/llama-3-2-90b-vision:default",
        "canonical_name": "Llama 3.2 90B (Vision)",
        "source_name": "Llama 3.2 90B (Vision)",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-3-2-90b-vision",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-2-instruct-90b-vision",
        "source_rank": 213,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 5,
        "aa_gpqa": 43,
        "aa_scicode": 24,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": 39,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.04,
        "aa_output_cost_usd_per_1m": 2.04,
        "aa_blended_cost_usd_per_1m": 2.04,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": 97.96,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 28.1,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 40.48,
        "llmdex_efficiency_score": 5,
        "llmdex_performance_rank": 213,
        "llmdex_value_rank": 170,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-3-3-70b:default",
        "family_id": "meta/llama-3-3-70b",
        "variant_id": "meta/llama-3-3-70b:default",
        "canonical_name": "Llama 3.3 70B",
        "source_name": "Llama 3.3 70B",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-3-3-70b",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-3-instruct-70b",
        "source_rank": 181,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 15.5,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 3,
        "aa_terminalbench_v21": 5,
        "aa_tau2": 27,
        "aa_tau3_banking": 1,
        "aa_lcr": 15,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 4,
        "aa_gpqa": 50,
        "aa_scicode": 26,
        "aa_ifbench": 47,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": 1,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.59,
        "aa_output_cost_usd_per_1m": 0.72,
        "aa_blended_cost_usd_per_1m": 0.642,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 83,
        "aa_speed_p5_tokens_per_second": 13,
        "aa_speed_p25_tokens_per_second": 44,
        "aa_speed_p75_tokens_per_second": 131,
        "aa_speed_p95_tokens_per_second": 309,
        "aa_latency_seconds": 1.69,
        "aa_latency_first_token_seconds": 1.69,
        "aa_latency_p5_seconds": 0.72,
        "aa_latency_p25_seconds": 1.12,
        "aa_latency_p75_seconds": 2.55,
        "aa_latency_p95_seconds": 6.69,
        "aa_total_response_time_seconds": 7.73,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.36,
        "llmdex_speed_index": 49.85,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 44.28,
        "llmdex_efficiency_score": 37.22,
        "llmdex_performance_rank": 181,
        "llmdex_value_rank": 142,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-4-maverick:default",
        "family_id": "meta/llama-4-maverick",
        "variant_id": "meta/llama-4-maverick:default",
        "canonical_name": "Llama 4 Maverick",
        "source_name": "Llama 4 Maverick",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-4-maverick",
        "source_model_url": "https://artificialanalysis.ai/models/llama-4-maverick",
        "source_rank": 150,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 20.5,
        "aa_omniscience_index": -42,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": 8,
        "aa_tau2": 18,
        "aa_tau3_banking": 4,
        "aa_lcr": 46,
        "aa_omniscience_accuracy": 24,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 5,
        "aa_gpqa": 67,
        "aa_scicode": 33,
        "aa_ifbench": 43,
        "aa_critpt": 0,
        "aa_mmmu_pro": 62,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.27,
        "aa_output_cost_usd_per_1m": 0.85,
        "aa_blended_cost_usd_per_1m": 0.502,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 111,
        "aa_speed_p5_tokens_per_second": 34,
        "aa_speed_p25_tokens_per_second": 58,
        "aa_speed_p75_tokens_per_second": 134,
        "aa_speed_p95_tokens_per_second": 229,
        "aa_latency_seconds": 0.92,
        "aa_latency_first_token_seconds": 0.92,
        "aa_latency_p5_seconds": 0.63,
        "aa_latency_p25_seconds": 0.82,
        "aa_latency_p75_seconds": 1.1,
        "aa_latency_p95_seconds": 1.77,
        "aa_total_response_time_seconds": 5.43,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 99.5,
        "llmdex_speed_index": 56.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 48.15,
        "llmdex_efficiency_score": 58.89,
        "llmdex_performance_rank": 150,
        "llmdex_value_rank": 114,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/llama-4-scout:default",
        "family_id": "meta/llama-4-scout",
        "variant_id": "meta/llama-4-scout:default",
        "canonical_name": "Llama 4 Scout",
        "source_name": "Llama 4 Scout",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-4-scout",
        "source_model_url": "https://artificialanalysis.ai/models/llama-4-scout",
        "source_rank": 175,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 10,
        "aa_official_coding_index": 10.5,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 10000000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": 4,
        "aa_tau2": 15,
        "aa_tau3_banking": 3,
        "aa_lcr": 26,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 22,
        "aa_hle": 4,
        "aa_gpqa": 59,
        "aa_scicode": 17,
        "aa_ifbench": 40,
        "aa_critpt": 0,
        "aa_mmmu_pro": 53,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.18,
        "aa_output_cost_usd_per_1m": 0.66,
        "aa_blended_cost_usd_per_1m": 0.372,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 96,
        "aa_speed_p5_tokens_per_second": 33,
        "aa_speed_p25_tokens_per_second": 58,
        "aa_speed_p75_tokens_per_second": 172,
        "aa_speed_p95_tokens_per_second": 448,
        "aa_latency_seconds": 0.77,
        "aa_latency_first_token_seconds": 0.77,
        "aa_latency_p5_seconds": 0.48,
        "aa_latency_p25_seconds": 0.65,
        "aa_latency_p75_seconds": 0.94,
        "aa_latency_p95_seconds": 1.51,
        "aa_total_response_time_seconds": 5.98,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 10,
        "llmdex_cost_index": 99.63,
        "llmdex_speed_index": 55.75,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.04,
        "llmdex_efficiency_score": 58.33,
        "llmdex_performance_rank": 175,
        "llmdex_value_rank": 133,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/muse-spark-1-1:xhigh",
        "family_id": "meta/muse-spark-1-1",
        "variant_id": "meta/muse-spark-1-1:xhigh",
        "canonical_name": "Muse Spark 1.1 (xhigh)",
        "source_name": "Muse Spark 1.1 (xhigh)",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "muse-spark-1-1-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/muse-spark-1-1",
        "source_rank": 18,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 51,
        "aa_official_coding_index": 68,
        "aa_omniscience_index": 18,
        "aa_context_window_tokens": 1050000,
        "aa_gdpval": 44,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 78,
        "aa_tau2": null,
        "aa_tau3_banking": 25,
        "aa_lcr": 63,
        "aa_omniscience_accuracy": 41,
        "aa_non_hallucination_rate": 62,
        "aa_hle": 45,
        "aa_gpqa": 90,
        "aa_scicode": 58,
        "aa_ifbench": null,
        "aa_critpt": 15,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 4.25,
        "aa_blended_cost_usd_per_1m": 2.45,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 117,
        "aa_speed_p5_tokens_per_second": 88,
        "aa_speed_p25_tokens_per_second": 110,
        "aa_speed_p75_tokens_per_second": 132,
        "aa_speed_p95_tokens_per_second": 157,
        "aa_latency_seconds": 1.47,
        "aa_latency_first_token_seconds": 18.58,
        "aa_latency_p5_seconds": 1.2,
        "aa_latency_p25_seconds": 1.27,
        "aa_latency_p75_seconds": 1.6,
        "aa_latency_p95_seconds": 53.3,
        "aa_total_response_time_seconds": 22.86,
        "aa_reasoning_time_seconds": 17.11,
        "llmdex_adjusted_performance": 51,
        "llmdex_cost_index": 97.55,
        "llmdex_speed_index": 54.35,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 65.64,
        "llmdex_efficiency_score": 51.67,
        "llmdex_performance_rank": 18,
        "llmdex_value_rank": 2,
        "llmdex_efficiency_rank": 31,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "meta/muse-spark:default",
        "family_id": "meta/muse-spark",
        "variant_id": "meta/muse-spark:default",
        "canonical_name": "Muse Spark",
        "source_name": "Muse Spark",
        "provider": "Meta",
        "creator": "Meta",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "muse-spark",
        "source_model_url": "https://artificialanalysis.ai/models/muse-spark",
        "source_rank": 35,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 43,
        "aa_official_coding_index": 57,
        "aa_omniscience_index": 4,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": 45,
        "aa_terminalbench_v21": 62,
        "aa_tau2": 92,
        "aa_tau3_banking": 20,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 45,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 40,
        "aa_gpqa": 88,
        "aa_scicode": 52,
        "aa_ifbench": 76,
        "aa_critpt": 11,
        "aa_mmmu_pro": 81,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 43,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 43,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 35,
        "llmdex_value_rank": 149,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "microsoft/phi-4-mini:default",
        "family_id": "microsoft/phi-4-mini",
        "variant_id": "microsoft/phi-4-mini:default",
        "canonical_name": "Phi-4 Mini",
        "source_name": "Phi-4 Mini",
        "provider": "Microsoft",
        "creator": "Microsoft",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "phi-4-mini",
        "source_model_url": "https://artificialanalysis.ai/models/phi-4-mini",
        "source_rank": 214,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 5.5,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 8,
        "aa_tau3_banking": 1,
        "aa_lcr": 14,
        "aa_omniscience_accuracy": 8,
        "aa_non_hallucination_rate": 24,
        "aa_hle": 4,
        "aa_gpqa": 33,
        "aa_scicode": 11,
        "aa_ifbench": 21,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 44,
        "aa_speed_p5_tokens_per_second": 37,
        "aa_speed_p25_tokens_per_second": 43,
        "aa_speed_p75_tokens_per_second": 46,
        "aa_speed_p95_tokens_per_second": 48,
        "aa_latency_seconds": 0.82,
        "aa_latency_first_token_seconds": 0.82,
        "aa_latency_p5_seconds": 0.79,
        "aa_latency_p25_seconds": 0.81,
        "aa_latency_p75_seconds": 0.85,
        "aa_latency_p95_seconds": 1.49,
        "aa_total_response_time_seconds": 12.17,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 50.3,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 43.06,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 214,
        "llmdex_value_rank": 148,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "microsoft/phi-4-multimodal:default",
        "family_id": "microsoft/phi-4-multimodal",
        "variant_id": "microsoft/phi-4-multimodal:default",
        "canonical_name": "Phi-4 Multimodal",
        "source_name": "Phi-4 Multimodal",
        "provider": "Microsoft",
        "creator": "Microsoft",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "phi-4-multimodal",
        "source_model_url": "https://artificialanalysis.ai/models/phi-4-multimodal",
        "source_rank": 227,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 11,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 4,
        "aa_gpqa": 32,
        "aa_scicode": 11,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": 15,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 18,
        "aa_speed_p5_tokens_per_second": 17,
        "aa_speed_p25_tokens_per_second": 17,
        "aa_speed_p75_tokens_per_second": 18,
        "aa_speed_p95_tokens_per_second": 18,
        "aa_latency_seconds": 0.85,
        "aa_latency_first_token_seconds": 0.85,
        "aa_latency_p5_seconds": 0.8,
        "aa_latency_p25_seconds": 0.83,
        "aa_latency_p75_seconds": 0.86,
        "aa_latency_p95_seconds": 2.27,
        "aa_total_response_time_seconds": 28.48,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 47.55,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.01,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 227,
        "llmdex_value_rank": 159,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "microsoft/phi-4:default",
        "family_id": "microsoft/phi-4",
        "variant_id": "microsoft/phi-4:default",
        "canonical_name": "Phi-4",
        "source_name": "Phi-4",
        "provider": "Microsoft",
        "creator": "Microsoft",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "phi-4",
        "source_model_url": "https://artificialanalysis.ai/models/phi-4",
        "source_rank": 223,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 26,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 16000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 19,
        "aa_hle": 4,
        "aa_gpqa": 57,
        "aa_scicode": 26,
        "aa_ifbench": 24,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.13,
        "aa_output_cost_usd_per_1m": 0.5,
        "aa_blended_cost_usd_per_1m": 0.278,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 99.72,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 40.52,
        "llmdex_efficiency_score": 46.67,
        "llmdex_performance_rank": 223,
        "llmdex_value_rank": 169,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "minimax/minimax-m3:default",
        "family_id": "minimax/minimax-m3",
        "variant_id": "minimax/minimax-m3:default",
        "canonical_name": "MiniMax-M3",
        "source_name": "MiniMax-M3",
        "provider": "MiniMax",
        "creator": "MiniMax",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "minimax-m3",
        "source_model_url": "https://artificialanalysis.ai/models/minimax-m3",
        "source_rank": 30,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 44,
        "aa_official_coding_index": 55,
        "aa_omniscience_index": 1,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 45,
        "aa_terminalbench_hard": 42,
        "aa_terminalbench_v21": 65,
        "aa_tau2": 89,
        "aa_tau3_banking": 13,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 84,
        "aa_hle": 37,
        "aa_gpqa": 93,
        "aa_scicode": 45,
        "aa_ifbench": 83,
        "aa_critpt": 4,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.3,
        "aa_output_cost_usd_per_1m": 1.2,
        "aa_blended_cost_usd_per_1m": 0.66,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 76,
        "aa_speed_p5_tokens_per_second": 45,
        "aa_speed_p25_tokens_per_second": 63,
        "aa_speed_p75_tokens_per_second": 106,
        "aa_speed_p95_tokens_per_second": 162,
        "aa_latency_seconds": 1.47,
        "aa_latency_first_token_seconds": 27.92,
        "aa_latency_p5_seconds": 1.03,
        "aa_latency_p25_seconds": 1.25,
        "aa_latency_p75_seconds": 1.85,
        "aa_latency_p95_seconds": 2.29,
        "aa_total_response_time_seconds": 34.53,
        "aa_reasoning_time_seconds": 26.45,
        "llmdex_adjusted_performance": 44,
        "llmdex_cost_index": 99.34,
        "llmdex_speed_index": 50.25,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.85,
        "llmdex_efficiency_score": 75,
        "llmdex_performance_rank": 30,
        "llmdex_value_rank": 4,
        "llmdex_efficiency_rank": 14,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/devstral-2:default",
        "family_id": "mistral-ai/devstral-2",
        "variant_id": "mistral-ai/devstral-2:default",
        "canonical_name": "Devstral 2",
        "source_name": "Devstral 2",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "devstral-2",
        "source_model_url": "https://artificialanalysis.ai/models/devstral-2",
        "source_rank": 122,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 19,
        "aa_official_coding_index": 31.5,
        "aa_omniscience_index": -46,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 12,
        "aa_terminalbench_hard": 19,
        "aa_terminalbench_v21": 30,
        "aa_tau2": 25,
        "aa_tau3_banking": 10,
        "aa_lcr": 30,
        "aa_omniscience_accuracy": 21,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 4,
        "aa_gpqa": 59,
        "aa_scicode": 33,
        "aa_ifbench": 38,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 20,
        "aa_speed_p5_tokens_per_second": 5,
        "aa_speed_p25_tokens_per_second": 15,
        "aa_speed_p75_tokens_per_second": 23,
        "aa_speed_p95_tokens_per_second": 40,
        "aa_latency_seconds": 1.31,
        "aa_latency_first_token_seconds": 1.31,
        "aa_latency_p5_seconds": 1.07,
        "aa_latency_p25_seconds": 1.15,
        "aa_latency_p75_seconds": 2.09,
        "aa_latency_p95_seconds": 5.65,
        "aa_total_response_time_seconds": 26.87,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 19,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 45.45,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 48.59,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 122,
        "llmdex_value_rank": 112,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/devstral-small-2:default",
        "family_id": "mistral-ai/devstral-small-2",
        "variant_id": "mistral-ai/devstral-small-2:default",
        "canonical_name": "Devstral Small 2",
        "source_name": "Devstral Small 2",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "devstral-small-2",
        "source_model_url": "https://artificialanalysis.ai/models/devstral-small-2",
        "source_rank": 132,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 29.5,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 12,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": 30,
        "aa_tau2": 23,
        "aa_tau3_banking": 10,
        "aa_lcr": 24,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 3,
        "aa_gpqa": 53,
        "aa_scicode": 29,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": 45,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 20,
        "aa_speed_p5_tokens_per_second": 4,
        "aa_speed_p25_tokens_per_second": 15,
        "aa_speed_p75_tokens_per_second": 36,
        "aa_speed_p95_tokens_per_second": 70,
        "aa_latency_seconds": 1.52,
        "aa_latency_first_token_seconds": 1.52,
        "aa_latency_p5_seconds": 1.06,
        "aa_latency_p25_seconds": 1.16,
        "aa_latency_p75_seconds": 2.32,
        "aa_latency_p95_seconds": 3.17,
        "aa_total_response_time_seconds": 26.42,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": 44.4,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.38,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 132,
        "llmdex_value_rank": 125,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/magistral-medium-1-2:medium",
        "family_id": "mistral-ai/magistral-medium-1-2",
        "variant_id": "mistral-ai/magistral-medium-1-2:medium",
        "canonical_name": "Magistral Medium 1.2",
        "source_name": "Magistral Medium 1.2",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "magistral-medium-1-2",
        "source_model_url": "https://artificialanalysis.ai/models/magistral-medium-2509",
        "source_rank": 128,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 25.5,
        "aa_omniscience_index": -26,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 13,
        "aa_terminalbench_v21": 12,
        "aa_tau2": 52,
        "aa_tau3_banking": 6,
        "aa_lcr": 51,
        "aa_omniscience_accuracy": 21,
        "aa_non_hallucination_rate": 41,
        "aa_hle": 10,
        "aa_gpqa": 74,
        "aa_scicode": 39,
        "aa_ifbench": 43,
        "aa_critpt": 0,
        "aa_mmmu_pro": 60,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 5,
        "aa_blended_cost_usd_per_1m": 3.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 44,
        "aa_speed_p5_tokens_per_second": 38,
        "aa_speed_p25_tokens_per_second": 42,
        "aa_speed_p75_tokens_per_second": 46,
        "aa_speed_p95_tokens_per_second": 47,
        "aa_latency_seconds": 1.72,
        "aa_latency_first_token_seconds": 46.76,
        "aa_latency_p5_seconds": 1.64,
        "aa_latency_p25_seconds": 1.66,
        "aa_latency_p75_seconds": 1.79,
        "aa_latency_p95_seconds": 2.27,
        "aa_total_response_time_seconds": 58.03,
        "aa_reasoning_time_seconds": 45.05,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": 96.8,
        "llmdex_speed_index": 45.8,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.2,
        "llmdex_efficiency_score": 17.22,
        "llmdex_performance_rank": 128,
        "llmdex_value_rank": 126,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/magistral-small-1-2:default",
        "family_id": "mistral-ai/magistral-small-1-2",
        "variant_id": "mistral-ai/magistral-small-1-2:default",
        "canonical_name": "Magistral Small 1.2",
        "source_name": "Magistral Small 1.2",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "magistral-small-1-2",
        "source_model_url": "https://artificialanalysis.ai/models/magistral-small-2509",
        "source_rank": 170,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 11,
        "aa_official_coding_index": 19.5,
        "aa_omniscience_index": -65,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": 4,
        "aa_tau2": 28,
        "aa_tau3_banking": 4,
        "aa_lcr": 16,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 6,
        "aa_gpqa": 66,
        "aa_scicode": 35,
        "aa_ifbench": 44,
        "aa_critpt": 0,
        "aa_mmmu_pro": 55,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 1.5,
        "aa_blended_cost_usd_per_1m": 0.9,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 89,
        "aa_speed_p5_tokens_per_second": 74,
        "aa_speed_p25_tokens_per_second": 84,
        "aa_speed_p75_tokens_per_second": 90,
        "aa_speed_p95_tokens_per_second": 93,
        "aa_latency_seconds": 0.94,
        "aa_latency_first_token_seconds": 23.39,
        "aa_latency_p5_seconds": 0.86,
        "aa_latency_p25_seconds": 0.9,
        "aa_latency_p75_seconds": 1.03,
        "aa_latency_p95_seconds": 2.03,
        "aa_total_response_time_seconds": 29,
        "aa_reasoning_time_seconds": 22.45,
        "llmdex_adjusted_performance": 11,
        "llmdex_cost_index": 99.1,
        "llmdex_speed_index": 54.2,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.07,
        "llmdex_efficiency_score": 33.33,
        "llmdex_performance_rank": 170,
        "llmdex_value_rank": 131,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/ministral-3-14b:default",
        "family_id": "mistral-ai/ministral-3-14b",
        "variant_id": "mistral-ai/ministral-3-14b:default",
        "canonical_name": "Ministral 3 14B",
        "source_name": "Ministral 3 14B",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ministral-3-14b",
        "source_model_url": "https://artificialanalysis.ai/models/ministral-3-14b",
        "source_rank": 172,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 11,
        "aa_official_coding_index": 17,
        "aa_omniscience_index": -67,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": 10,
        "aa_tau2": 27,
        "aa_tau3_banking": 7,
        "aa_lcr": 22,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 5,
        "aa_gpqa": 57,
        "aa_scicode": 24,
        "aa_ifbench": 32,
        "aa_critpt": 0,
        "aa_mmmu_pro": 50,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.2,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 69,
        "aa_speed_p5_tokens_per_second": 12,
        "aa_speed_p25_tokens_per_second": 63,
        "aa_speed_p75_tokens_per_second": 83,
        "aa_speed_p95_tokens_per_second": 88,
        "aa_latency_seconds": 0.89,
        "aa_latency_first_token_seconds": 0.89,
        "aa_latency_p5_seconds": 0.79,
        "aa_latency_p25_seconds": 0.83,
        "aa_latency_p75_seconds": 1.45,
        "aa_latency_p95_seconds": 5.05,
        "aa_total_response_time_seconds": 8.15,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 11,
        "llmdex_cost_index": 99.8,
        "llmdex_speed_index": 52.45,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 45.93,
        "llmdex_efficiency_score": 70.56,
        "llmdex_performance_rank": 172,
        "llmdex_value_rank": 134,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/ministral-3-3b:default",
        "family_id": "mistral-ai/ministral-3-3b",
        "variant_id": "mistral-ai/ministral-3-3b:default",
        "canonical_name": "Ministral 3 3B",
        "source_name": "Ministral 3 3B",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ministral-3-3b",
        "source_model_url": "https://artificialanalysis.ai/models/ministral-3-3b",
        "source_rank": 210,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": 7,
        "aa_omniscience_index": -64,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 25,
        "aa_tau3_banking": 5,
        "aa_lcr": 12,
        "aa_omniscience_accuracy": 8,
        "aa_non_hallucination_rate": 22,
        "aa_hle": 5,
        "aa_gpqa": 30,
        "aa_scicode": 14,
        "aa_ifbench": 24,
        "aa_critpt": 0,
        "aa_mmmu_pro": 38,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.1,
        "aa_blended_cost_usd_per_1m": 0.1,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 259,
        "aa_speed_p5_tokens_per_second": 181,
        "aa_speed_p25_tokens_per_second": 239,
        "aa_speed_p75_tokens_per_second": 284,
        "aa_speed_p95_tokens_per_second": 295,
        "aa_latency_seconds": 0.65,
        "aa_latency_first_token_seconds": 0.65,
        "aa_latency_p5_seconds": 0.56,
        "aa_latency_p25_seconds": 0.59,
        "aa_latency_p75_seconds": 0.77,
        "aa_latency_p95_seconds": 1.88,
        "aa_total_response_time_seconds": 2.58,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": 99.9,
        "llmdex_speed_index": 72.65,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.5,
        "llmdex_efficiency_score": 71.39,
        "llmdex_performance_rank": 210,
        "llmdex_value_rank": 124,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/ministral-3-8b:default",
        "family_id": "mistral-ai/ministral-3-8b",
        "variant_id": "mistral-ai/ministral-3-8b:default",
        "canonical_name": "Ministral 3 8B",
        "source_name": "Ministral 3 8B",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "ministral-3-8b",
        "source_model_url": "https://artificialanalysis.ai/models/ministral-3-8b",
        "source_rank": 187,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 12.5,
        "aa_omniscience_index": -68,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": 4,
        "aa_tau2": 27,
        "aa_tau3_banking": 4,
        "aa_lcr": 24,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 4,
        "aa_gpqa": 47,
        "aa_scicode": 21,
        "aa_ifbench": 29,
        "aa_critpt": 0,
        "aa_mmmu_pro": 46,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.15,
        "aa_output_cost_usd_per_1m": 0.15,
        "aa_blended_cost_usd_per_1m": 0.15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 121,
        "aa_speed_p5_tokens_per_second": 77,
        "aa_speed_p25_tokens_per_second": 95,
        "aa_speed_p75_tokens_per_second": 132,
        "aa_speed_p95_tokens_per_second": 150,
        "aa_latency_seconds": 0.72,
        "aa_latency_first_token_seconds": 0.72,
        "aa_latency_p5_seconds": 0.67,
        "aa_latency_p25_seconds": 0.7,
        "aa_latency_p75_seconds": 0.84,
        "aa_latency_p95_seconds": 0.94,
        "aa_total_response_time_seconds": 4.85,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.85,
        "llmdex_speed_index": 58.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 46.16,
        "llmdex_efficiency_score": 71.39,
        "llmdex_performance_rank": 187,
        "llmdex_value_rank": 130,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/mistral-large-3:default",
        "family_id": "mistral-ai/mistral-large-3",
        "variant_id": "mistral-ai/mistral-large-3:default",
        "canonical_name": "Mistral Large 3",
        "source_name": "Mistral Large 3",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mistral-large-3",
        "source_model_url": "https://artificialanalysis.ai/models/mistral-large-3",
        "source_rank": 142,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 16,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": -39,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 7,
        "aa_terminalbench_hard": 16,
        "aa_terminalbench_v21": 12,
        "aa_tau2": 25,
        "aa_tau3_banking": 6,
        "aa_lcr": 35,
        "aa_omniscience_accuracy": 24,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 4,
        "aa_gpqa": 68,
        "aa_scicode": 36,
        "aa_ifbench": 36,
        "aa_critpt": 0,
        "aa_mmmu_pro": 56,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 1.5,
        "aa_blended_cost_usd_per_1m": 0.9,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 49,
        "aa_speed_p5_tokens_per_second": 44,
        "aa_speed_p25_tokens_per_second": 46,
        "aa_speed_p75_tokens_per_second": 55,
        "aa_speed_p95_tokens_per_second": 67,
        "aa_latency_seconds": 1.16,
        "aa_latency_first_token_seconds": 1.16,
        "aa_latency_p5_seconds": 1.01,
        "aa_latency_p25_seconds": 1.08,
        "aa_latency_p75_seconds": 1.45,
        "aa_latency_p95_seconds": 2.67,
        "aa_total_response_time_seconds": 11.42,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 16,
        "llmdex_cost_index": 99.1,
        "llmdex_speed_index": 49.1,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.55,
        "llmdex_efficiency_score": 45.28,
        "llmdex_performance_rank": 142,
        "llmdex_value_rank": 120,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/mistral-medium-3-5:medium",
        "family_id": "mistral-ai/mistral-medium-3-5",
        "variant_id": "mistral-ai/mistral-medium-3-5:medium",
        "canonical_name": "Mistral Medium 3.5",
        "source_name": "Mistral Medium 3.5",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mistral-medium-3-5",
        "source_model_url": "https://artificialanalysis.ai/models/mistral-medium-3-5",
        "source_rank": 80,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 30,
        "aa_official_coding_index": 45.5,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 22,
        "aa_terminalbench_hard": 33,
        "aa_terminalbench_v21": 51,
        "aa_tau2": 94,
        "aa_tau3_banking": 14,
        "aa_lcr": 61,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 13,
        "aa_gpqa": 75,
        "aa_scicode": 40,
        "aa_ifbench": 69,
        "aa_critpt": 0,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.5,
        "aa_output_cost_usd_per_1m": 7.5,
        "aa_blended_cost_usd_per_1m": 3.9,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 84,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 156,
        "aa_speed_p95_tokens_per_second": 175,
        "aa_latency_seconds": 2.17,
        "aa_latency_first_token_seconds": 25.84,
        "aa_latency_p5_seconds": 1.48,
        "aa_latency_p25_seconds": 1.72,
        "aa_latency_p75_seconds": 2.45,
        "aa_latency_p95_seconds": 2.88,
        "aa_total_response_time_seconds": 31.75,
        "aa_reasoning_time_seconds": 23.67,
        "llmdex_adjusted_performance": 30,
        "llmdex_cost_index": 96.1,
        "llmdex_speed_index": 47.55,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 53.34,
        "llmdex_efficiency_score": 23.89,
        "llmdex_performance_rank": 80,
        "llmdex_value_rank": 79,
        "llmdex_efficiency_rank": 61,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/mistral-small-4:default",
        "family_id": "mistral-ai/mistral-small-4",
        "variant_id": "mistral-ai/mistral-small-4:default",
        "canonical_name": "Mistral Small 4",
        "source_name": "Mistral Small 4",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mistral-small-4",
        "source_model_url": "https://artificialanalysis.ai/models/mistral-small-4",
        "source_rank": 121,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 20,
        "aa_official_coding_index": 29.5,
        "aa_omniscience_index": -30,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 5,
        "aa_terminalbench_hard": 17,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 41,
        "aa_tau3_banking": 5,
        "aa_lcr": 45,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 33,
        "aa_hle": 9,
        "aa_gpqa": 77,
        "aa_scicode": 38,
        "aa_ifbench": 48,
        "aa_critpt": 0,
        "aa_mmmu_pro": 57,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.15,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.33,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 160,
        "aa_speed_p5_tokens_per_second": 104,
        "aa_speed_p25_tokens_per_second": 141,
        "aa_speed_p75_tokens_per_second": 182,
        "aa_speed_p95_tokens_per_second": 199,
        "aa_latency_seconds": 0.8,
        "aa_latency_first_token_seconds": 13.3,
        "aa_latency_p5_seconds": 0.65,
        "aa_latency_p25_seconds": 0.69,
        "aa_latency_p75_seconds": 0.99,
        "aa_latency_p95_seconds": 1.24,
        "aa_total_response_time_seconds": 16.42,
        "aa_reasoning_time_seconds": 12.5,
        "llmdex_adjusted_performance": 20,
        "llmdex_cost_index": 99.67,
        "llmdex_speed_index": 62,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.3,
        "llmdex_efficiency_score": 72.22,
        "llmdex_performance_rank": 121,
        "llmdex_value_rank": 88,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "mistral-ai/mistral-small-4:non-reasoning",
        "family_id": "mistral-ai/mistral-small-4",
        "variant_id": "mistral-ai/mistral-small-4:non-reasoning",
        "canonical_name": "Mistral Small 4 (non-reasoning)",
        "source_name": "Mistral Small 4 (non-reasoning)",
        "provider": "Mistral AI",
        "creator": "Mistral",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "mistral-small-4-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/mistral-small-4-non-reasoning",
        "source_rank": 163,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": null,
        "aa_tau2": 18,
        "aa_tau3_banking": null,
        "aa_lcr": 21,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 23,
        "aa_hle": 4,
        "aa_gpqa": 57,
        "aa_scicode": 28,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": 46,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.15,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.33,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 145,
        "aa_speed_p5_tokens_per_second": 114,
        "aa_speed_p25_tokens_per_second": 137,
        "aa_speed_p75_tokens_per_second": 180,
        "aa_speed_p95_tokens_per_second": 197,
        "aa_latency_seconds": 0.72,
        "aa_latency_first_token_seconds": 0.72,
        "aa_latency_p5_seconds": 0.64,
        "aa_latency_p25_seconds": 0.68,
        "aa_latency_p75_seconds": 0.76,
        "aa_latency_p95_seconds": 0.8,
        "aa_total_response_time_seconds": 4.18,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": 99.67,
        "llmdex_speed_index": 60.9,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 48.08,
        "llmdex_efficiency_score": 62.78,
        "llmdex_performance_rank": 163,
        "llmdex_value_rank": 115,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "motif-technologies/motif-2-12-7b:default",
        "family_id": "motif-technologies/motif-2-12-7b",
        "variant_id": "motif-technologies/motif-2-12-7b:default",
        "canonical_name": "Motif-2-12.7B",
        "source_name": "Motif-2-12.7B",
        "provider": "Motif Technologies",
        "creator": "Motif Technologies",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "motif-2-12-7b",
        "source_model_url": "https://artificialanalysis.ai/models/motif-2-12-7b",
        "source_rank": 159,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 13,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -61,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 46,
        "aa_tau3_banking": null,
        "aa_lcr": 13,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 8,
        "aa_gpqa": 69,
        "aa_scicode": 28,
        "aa_ifbench": 57,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 13,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 13,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 159,
        "llmdex_value_rank": 209,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "motif-technologies/motif-3-beta:default",
        "family_id": "motif-technologies/motif-3-beta",
        "variant_id": "motif-technologies/motif-3-beta:default",
        "canonical_name": "Motif 3 (Beta)",
        "source_name": "Motif 3 (Beta)",
        "provider": "Motif Technologies",
        "creator": "Motif Technologies",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "motif-3-beta",
        "source_model_url": "https://artificialanalysis.ai/models/motif-0714",
        "source_rank": 33,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 44,
        "aa_official_coding_index": 57.5,
        "aa_omniscience_index": -17,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 38,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 71,
        "aa_tau2": null,
        "aa_tau3_banking": 29,
        "aa_lcr": 61,
        "aa_omniscience_accuracy": 21,
        "aa_non_hallucination_rate": 51,
        "aa_hle": 38,
        "aa_gpqa": 87,
        "aa_scicode": 44,
        "aa_ifbench": null,
        "aa_critpt": 6,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 44,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 44,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 33,
        "llmdex_value_rank": 144,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "multiverse-computing/hypernova-60b-2605:default",
        "family_id": "multiverse-computing/hypernova-60b-2605",
        "variant_id": "multiverse-computing/hypernova-60b-2605:default",
        "canonical_name": "HyperNova 60B 2605",
        "source_name": "HyperNova 60B 2605",
        "provider": "Multiverse Computing",
        "creator": "Multiverse Computing",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hypernova-60b-2605",
        "source_model_url": "https://artificialanalysis.ai/models/hypernova-60b",
        "source_rank": 130,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 25.5,
        "aa_omniscience_index": -56,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 8,
        "aa_terminalbench_hard": 23,
        "aa_terminalbench_v21": 18,
        "aa_tau2": 63,
        "aa_tau3_banking": 5,
        "aa_lcr": 32,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 15,
        "aa_gpqa": 73,
        "aa_scicode": 33,
        "aa_ifbench": 66,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.04,
        "aa_output_cost_usd_per_1m": 0.14,
        "aa_blended_cost_usd_per_1m": 0.08,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 414,
        "aa_speed_p5_tokens_per_second": 282,
        "aa_speed_p25_tokens_per_second": 351,
        "aa_speed_p75_tokens_per_second": 458,
        "aa_speed_p95_tokens_per_second": 570,
        "aa_latency_seconds": 0.65,
        "aa_latency_first_token_seconds": 5.47,
        "aa_latency_p5_seconds": 0.27,
        "aa_latency_p25_seconds": 0.53,
        "aa_latency_p75_seconds": 0.92,
        "aa_latency_p95_seconds": 1.14,
        "aa_total_response_time_seconds": 6.68,
        "aa_reasoning_time_seconds": 4.83,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": 99.92,
        "llmdex_speed_index": 88.15,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.61,
        "llmdex_efficiency_score": 91.11,
        "llmdex_performance_rank": 130,
        "llmdex_value_rank": 45,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nanbeige/nanbeige4-1-3b:default",
        "family_id": "nanbeige/nanbeige4-1-3b",
        "variant_id": "nanbeige/nanbeige4-1-3b:default",
        "canonical_name": "Nanbeige4.1-3B",
        "source_name": "Nanbeige4.1-3B",
        "provider": "Nanbeige",
        "creator": "Nanbeige",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nanbeige4-1-3b",
        "source_model_url": "https://artificialanalysis.ai/models/nanbeige4-1-3b",
        "source_rank": 171,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 11,
        "aa_official_coding_index": 14,
        "aa_omniscience_index": -42,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 1,
        "aa_tau2": 22,
        "aa_tau3_banking": 0,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 43,
        "aa_hle": 10,
        "aa_gpqa": 85,
        "aa_scicode": 27,
        "aa_ifbench": 35,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 11,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 11,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 171,
        "llmdex_value_rank": 215,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "naver/hyperclova-x-seed-think-32b:default",
        "family_id": "naver/hyperclova-x-seed-think-32b",
        "variant_id": "naver/hyperclova-x-seed-think-32b:default",
        "canonical_name": "HyperCLOVA X SEED Think (32B)",
        "source_name": "HyperCLOVA X SEED Think (32B)",
        "provider": "Naver",
        "creator": "Naver",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hyperclova-x-seed-think-32b",
        "source_model_url": "https://artificialanalysis.ai/models/hyperclova-x-seed-think-32b",
        "source_rank": 135,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 17,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -53,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 12,
        "aa_terminalbench_v21": null,
        "aa_tau2": 87,
        "aa_tau3_banking": null,
        "aa_lcr": 12,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 21,
        "aa_hle": 5,
        "aa_gpqa": 62,
        "aa_scicode": 28,
        "aa_ifbench": 38,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 17,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 17,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 135,
        "llmdex_value_rank": 198,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nex-agi/nex-n2-pro:default",
        "family_id": "nex-agi/nex-n2-pro",
        "variant_id": "nex-agi/nex-n2-pro:default",
        "canonical_name": "Nex-N2-Pro",
        "source_name": "Nex-N2-Pro",
        "provider": "Nex AGI",
        "creator": "Nex AGI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nex-n2-pro",
        "source_model_url": "https://artificialanalysis.ai/models/nex-n2-pro",
        "source_rank": 42,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 41,
        "aa_official_coding_index": 55,
        "aa_omniscience_index": -28,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 38,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 68,
        "aa_tau2": 82,
        "aa_tau3_banking": 17,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 34,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 32,
        "aa_gpqa": 89,
        "aa_scicode": 42,
        "aa_ifbench": 66,
        "aa_critpt": 9,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.5,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 136,
        "aa_speed_p5_tokens_per_second": 112,
        "aa_speed_p25_tokens_per_second": 129,
        "aa_speed_p75_tokens_per_second": 145,
        "aa_speed_p95_tokens_per_second": 155,
        "aa_latency_seconds": 1.76,
        "aa_latency_first_token_seconds": 16.51,
        "aa_latency_p5_seconds": 1.24,
        "aa_latency_p25_seconds": 1.34,
        "aa_latency_p75_seconds": 1.94,
        "aa_latency_p95_seconds": 2.13,
        "aa_total_response_time_seconds": 20.2,
        "aa_reasoning_time_seconds": 14.75,
        "llmdex_adjusted_performance": 41,
        "llmdex_cost_index": 98.7,
        "llmdex_speed_index": 54.8,
        "llmdex_coverage_score": 81.2,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.07,
        "llmdex_efficiency_score": 61.67,
        "llmdex_performance_rank": 42,
        "llmdex_value_rank": 10,
        "llmdex_efficiency_rank": 24,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/deephermes-3-llama-3-1-8b:default",
        "family_id": "nous-research/deephermes-3-llama-3-1-8b",
        "variant_id": "nous-research/deephermes-3-llama-3-1-8b:default",
        "canonical_name": "DeepHermes 3 - Llama-3.1 8B",
        "source_name": "DeepHermes 3 - Llama-3.1 8B",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "deephermes-3-llama-3-1-8b",
        "source_model_url": "https://artificialanalysis.ai/models/deephermes-3-llama-3-1-8b-preview",
        "source_rank": 247,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 9,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 4,
        "aa_gpqa": 27,
        "aa_scicode": 9,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 18.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 2,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 247,
        "llmdex_value_rank": 248,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/deephermes-3-mistral-24b:default",
        "family_id": "nous-research/deephermes-3-mistral-24b",
        "variant_id": "nous-research/deephermes-3-mistral-24b:default",
        "canonical_name": "DeepHermes 3 - Mistral 24B",
        "source_name": "DeepHermes 3 - Mistral 24B",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "deephermes-3-mistral-24b",
        "source_model_url": "https://artificialanalysis.ai/models/deephermes-3-mistral-24b-preview",
        "source_rank": 218,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 23,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": 4,
        "aa_gpqa": 38,
        "aa_scicode": 23,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 18.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 5,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 218,
        "llmdex_value_rank": 232,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/hermes-4-405b:default",
        "family_id": "nous-research/hermes-4-405b",
        "variant_id": "nous-research/hermes-4-405b:default",
        "canonical_name": "Hermes 4 405B",
        "source_name": "Hermes 4 405B",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "hermes-4-405b",
        "source_model_url": "https://artificialanalysis.ai/models/hermes-4-llama-3-1-405b",
        "source_rank": 191,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -33,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 10,
        "aa_terminalbench_v21": null,
        "aa_tau2": 27,
        "aa_tau3_banking": null,
        "aa_lcr": 20,
        "aa_omniscience_accuracy": 26,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 4,
        "aa_gpqa": 54,
        "aa_scicode": 35,
        "aa_ifbench": 35,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 3,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 40,
        "aa_speed_p5_tokens_per_second": 29,
        "aa_speed_p25_tokens_per_second": 34,
        "aa_speed_p75_tokens_per_second": 44,
        "aa_speed_p95_tokens_per_second": 46,
        "aa_latency_seconds": 2.36,
        "aa_latency_first_token_seconds": 2.36,
        "aa_latency_p5_seconds": 2.29,
        "aa_latency_p25_seconds": 2.33,
        "aa_latency_p75_seconds": 2.48,
        "aa_latency_p95_seconds": 3.53,
        "aa_total_response_time_seconds": 14.71,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 42.2,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.4,
        "llmdex_efficiency_score": 15.28,
        "llmdex_performance_rank": 191,
        "llmdex_value_rank": 153,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/hermes-4-405b:reasoning",
        "family_id": "nous-research/hermes-4-405b",
        "variant_id": "nous-research/hermes-4-405b:reasoning",
        "canonical_name": "Hermes 4 405B (reasoning)",
        "source_name": "Hermes 4 405B (reasoning)",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hermes-4-405b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/hermes-4-llama-3-1-405b-reasoning",
        "source_rank": 184,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": null,
        "aa_tau2": 22,
        "aa_tau3_banking": null,
        "aa_lcr": 21,
        "aa_omniscience_accuracy": 30,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 10,
        "aa_gpqa": 73,
        "aa_scicode": 25,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 3,
        "aa_blended_cost_usd_per_1m": 1.8,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 39,
        "aa_speed_p5_tokens_per_second": 27,
        "aa_speed_p25_tokens_per_second": 36,
        "aa_speed_p75_tokens_per_second": 43,
        "aa_speed_p95_tokens_per_second": 45,
        "aa_latency_seconds": 2.37,
        "aa_latency_first_token_seconds": 53.84,
        "aa_latency_p5_seconds": 2.28,
        "aa_latency_p25_seconds": 2.34,
        "aa_latency_p75_seconds": 2.48,
        "aa_latency_p95_seconds": 2.98,
        "aa_total_response_time_seconds": 66.71,
        "aa_reasoning_time_seconds": 51.47,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 98.2,
        "llmdex_speed_index": 42.05,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.37,
        "llmdex_efficiency_score": 15.28,
        "llmdex_performance_rank": 184,
        "llmdex_value_rank": 155,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/hermes-4-70b:default",
        "family_id": "nous-research/hermes-4-70b",
        "variant_id": "nous-research/hermes-4-70b:default",
        "canonical_name": "Hermes 4 70B",
        "source_name": "Hermes 4 70B",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "hermes-4-70b",
        "source_model_url": "https://artificialanalysis.ai/models/hermes-4-llama-3-1-70b",
        "source_rank": 205,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -47,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 22,
        "aa_tau3_banking": null,
        "aa_lcr": 2,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 20,
        "aa_hle": 4,
        "aa_gpqa": 49,
        "aa_scicode": 28,
        "aa_ifbench": 29,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.13,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.238,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 94,
        "aa_speed_p5_tokens_per_second": 73,
        "aa_speed_p25_tokens_per_second": 91,
        "aa_speed_p75_tokens_per_second": 100,
        "aa_speed_p95_tokens_per_second": 108,
        "aa_latency_seconds": 1.34,
        "aa_latency_first_token_seconds": 1.34,
        "aa_latency_p5_seconds": 1.3,
        "aa_latency_p25_seconds": 1.31,
        "aa_latency_p75_seconds": 1.37,
        "aa_latency_p95_seconds": 1.59,
        "aa_total_response_time_seconds": 6.64,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": 99.76,
        "llmdex_speed_index": 52.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 43.97,
        "llmdex_efficiency_score": 59.44,
        "llmdex_performance_rank": 205,
        "llmdex_value_rank": 145,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nous-research/hermes-4-70b:reasoning",
        "family_id": "nous-research/hermes-4-70b",
        "variant_id": "nous-research/hermes-4-70b:reasoning",
        "canonical_name": "Hermes 4 70B (reasoning)",
        "source_name": "Hermes 4 70B (reasoning)",
        "provider": "Nous Research",
        "creator": "Nous Research",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hermes-4-70b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/hermes-4-llama-3-1-70b-reasoning",
        "source_rank": 176,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 10,
        "aa_official_coding_index": 34,
        "aa_omniscience_index": -50,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 23,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 23,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 8,
        "aa_gpqa": 70,
        "aa_scicode": 34,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.13,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.238,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 93,
        "aa_speed_p5_tokens_per_second": 66,
        "aa_speed_p25_tokens_per_second": 85,
        "aa_speed_p75_tokens_per_second": 98,
        "aa_speed_p95_tokens_per_second": 103,
        "aa_latency_seconds": 1.37,
        "aa_latency_first_token_seconds": 22.88,
        "aa_latency_p5_seconds": 1.3,
        "aa_latency_p25_seconds": 1.34,
        "aa_latency_p75_seconds": 1.55,
        "aa_latency_p95_seconds": 3.93,
        "aa_total_response_time_seconds": 28.26,
        "aa_reasoning_time_seconds": 21.51,
        "llmdex_adjusted_performance": 10,
        "llmdex_cost_index": 99.76,
        "llmdex_speed_index": 52.45,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 45.42,
        "llmdex_efficiency_score": 64.44,
        "llmdex_performance_rank": 176,
        "llmdex_value_rank": 136,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/llama-3-1-nemotron-70b:default",
        "family_id": "nvidia/llama-3-1-nemotron-70b",
        "variant_id": "nvidia/llama-3-1-nemotron-70b:default",
        "canonical_name": "Llama 3.1 Nemotron 70B",
        "source_name": "Llama 3.1 Nemotron 70B",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-3-1-nemotron-70b",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-1-nemotron-instruct-70b",
        "source_rank": 202,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 8,
        "aa_official_coding_index": 23,
        "aa_omniscience_index": -41,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 23,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 31,
        "aa_hle": 5,
        "aa_gpqa": 46,
        "aa_scicode": 23,
        "aa_ifbench": 31,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.2,
        "aa_output_cost_usd_per_1m": 1.2,
        "aa_blended_cost_usd_per_1m": 1.2,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 82,
        "aa_speed_p5_tokens_per_second": 25,
        "aa_speed_p25_tokens_per_second": 57,
        "aa_speed_p75_tokens_per_second": 103,
        "aa_speed_p95_tokens_per_second": 129,
        "aa_latency_seconds": 8.99,
        "aa_latency_first_token_seconds": 8.99,
        "aa_latency_p5_seconds": 1.3,
        "aa_latency_p25_seconds": 3.18,
        "aa_latency_p75_seconds": 14.68,
        "aa_latency_p95_seconds": 46,
        "aa_total_response_time_seconds": 15.06,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 8,
        "llmdex_cost_index": 98.8,
        "llmdex_speed_index": 13.25,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 36.29,
        "llmdex_efficiency_score": 20,
        "llmdex_performance_rank": 202,
        "llmdex_value_rank": 183,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/llama-nemotron-super-49b-v1-5:default",
        "family_id": "nvidia/llama-nemotron-super-49b-v1-5",
        "variant_id": "nvidia/llama-nemotron-super-49b-v1-5:default",
        "canonical_name": "Llama Nemotron Super 49B v1.5",
        "source_name": "Llama Nemotron Super 49B v1.5",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "llama-nemotron-super-49b-v1-5",
        "source_model_url": "https://artificialanalysis.ai/models/llama-nemotron-super-49b-v1-5",
        "source_rank": 193,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": -46,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 4,
        "aa_terminalbench_v21": null,
        "aa_tau2": 25,
        "aa_tau3_banking": null,
        "aa_lcr": 22,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 34,
        "aa_hle": 4,
        "aa_gpqa": 48,
        "aa_scicode": 24,
        "aa_ifbench": 33,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.4,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 76,
        "aa_speed_p5_tokens_per_second": 23,
        "aa_speed_p25_tokens_per_second": 33,
        "aa_speed_p75_tokens_per_second": 121,
        "aa_speed_p95_tokens_per_second": 178,
        "aa_latency_seconds": 8.21,
        "aa_latency_first_token_seconds": 8.21,
        "aa_latency_p5_seconds": 1.71,
        "aa_latency_p25_seconds": 2.79,
        "aa_latency_p75_seconds": 19.14,
        "aa_latency_p95_seconds": 35.04,
        "aa_total_response_time_seconds": 14.82,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.6,
        "llmdex_speed_index": 16.55,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 37.69,
        "llmdex_efficiency_score": 54.44,
        "llmdex_performance_rank": 193,
        "llmdex_value_rank": 182,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/llama-nemotron-super-49b-v1-5:reasoning",
        "family_id": "nvidia/llama-nemotron-super-49b-v1-5",
        "variant_id": "nvidia/llama-nemotron-super-49b-v1-5:reasoning",
        "canonical_name": "Llama Nemotron Super 49B v1.5 (reasoning)",
        "source_name": "Llama Nemotron Super 49B v1.5 (reasoning)",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-nemotron-super-49b-v1-5-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/llama-nemotron-super-49b-v1-5-reasoning",
        "source_rank": 162,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -46,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 28,
        "aa_tau3_banking": null,
        "aa_lcr": 34,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 24,
        "aa_hle": 7,
        "aa_gpqa": 75,
        "aa_scicode": 35,
        "aa_ifbench": 37,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.4,
        "aa_output_cost_usd_per_1m": 0.4,
        "aa_blended_cost_usd_per_1m": 0.4,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 72,
        "aa_speed_p5_tokens_per_second": 22,
        "aa_speed_p25_tokens_per_second": 41,
        "aa_speed_p75_tokens_per_second": 116,
        "aa_speed_p95_tokens_per_second": 165,
        "aa_latency_seconds": 6.9,
        "aa_latency_first_token_seconds": 34.65,
        "aa_latency_p5_seconds": 1.61,
        "aa_latency_p25_seconds": 2,
        "aa_latency_p75_seconds": 21.05,
        "aa_latency_p95_seconds": 33.74,
        "aa_total_response_time_seconds": 41.59,
        "aa_reasoning_time_seconds": 27.76,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": 99.6,
        "llmdex_speed_index": 22.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 40.42,
        "llmdex_efficiency_score": 60,
        "llmdex_performance_rank": 162,
        "llmdex_value_rank": 171,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/llama-nemotron-ultra:reasoning",
        "family_id": "nvidia/llama-nemotron-ultra",
        "variant_id": "nvidia/llama-nemotron-ultra:reasoning",
        "canonical_name": "Llama Nemotron Ultra (reasoning)",
        "source_name": "Llama Nemotron Ultra (reasoning)",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "llama-nemotron-ultra-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/llama-3-1-nemotron-ultra-253b-v1-reasoning",
        "source_rank": 182,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 35,
        "aa_omniscience_index": -46,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 11,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 8,
        "aa_gpqa": 73,
        "aa_scicode": 35,
        "aa_ifbench": 38,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.6,
        "aa_output_cost_usd_per_1m": 1.8,
        "aa_blended_cost_usd_per_1m": 1.08,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 53,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 53,
        "aa_speed_p95_tokens_per_second": 55,
        "aa_latency_seconds": 2.32,
        "aa_latency_first_token_seconds": 40.13,
        "aa_latency_p5_seconds": 2.27,
        "aa_latency_p25_seconds": 2.28,
        "aa_latency_p75_seconds": 2.37,
        "aa_latency_p95_seconds": 2.73,
        "aa_total_response_time_seconds": 49.58,
        "aa_reasoning_time_seconds": 37.8,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 98.92,
        "llmdex_speed_index": 43.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 42.92,
        "llmdex_efficiency_score": 25.56,
        "llmdex_performance_rank": 182,
        "llmdex_value_rank": 150,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:reasoning",
        "family_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
        "variant_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:reasoning",
        "canonical_name": "Nemotron 3 Nano Omni 30B A3B Reasoning",
        "source_name": "Nemotron 3 Nano Omni 30B A3B Reasoning",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nemotron-3-nano-omni-30b-a3b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/nemotron-3-nano-omni-30b-a3b",
        "source_rank": 145,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 15,
        "aa_official_coding_index": 17.5,
        "aa_omniscience_index": -56,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": 7,
        "aa_tau2": 45,
        "aa_tau3_banking": null,
        "aa_lcr": 36,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 17,
        "aa_hle": 5,
        "aa_gpqa": 47,
        "aa_scicode": 28,
        "aa_ifbench": 63,
        "aa_critpt": 0,
        "aa_mmmu_pro": 53,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.07,
        "aa_output_cost_usd_per_1m": 0.3,
        "aa_blended_cost_usd_per_1m": 0.162,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 314,
        "aa_speed_p5_tokens_per_second": 287,
        "aa_speed_p25_tokens_per_second": 300,
        "aa_speed_p75_tokens_per_second": 326,
        "aa_speed_p95_tokens_per_second": 337,
        "aa_latency_seconds": 0.97,
        "aa_latency_first_token_seconds": 7.34,
        "aa_latency_p5_seconds": 0.93,
        "aa_latency_p25_seconds": 0.94,
        "aa_latency_p75_seconds": 1.04,
        "aa_latency_p95_seconds": 1.97,
        "aa_total_response_time_seconds": 8.94,
        "aa_reasoning_time_seconds": 6.38,
        "llmdex_adjusted_performance": 15,
        "llmdex_cost_index": 99.84,
        "llmdex_speed_index": 76.55,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.76,
        "llmdex_efficiency_score": 80,
        "llmdex_performance_rank": 145,
        "llmdex_value_rank": 82,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nemotron-3-ultra:default",
        "family_id": "nvidia/nemotron-3-ultra",
        "variant_id": "nvidia/nemotron-3-ultra:default",
        "canonical_name": "Nemotron 3 Ultra",
        "source_name": "Nemotron 3 Ultra",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nemotron-3-ultra",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b",
        "source_rank": 51,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 38,
        "aa_official_coding_index": 47,
        "aa_omniscience_index": -1,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 33,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": 54,
        "aa_tau2": 83,
        "aa_tau3_banking": 14,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 71,
        "aa_hle": 27,
        "aa_gpqa": 87,
        "aa_scicode": 40,
        "aa_ifbench": 81,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.68,
        "aa_output_cost_usd_per_1m": 2.67,
        "aa_blended_cost_usd_per_1m": 1.476,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 182,
        "aa_speed_p5_tokens_per_second": 44,
        "aa_speed_p25_tokens_per_second": 80,
        "aa_speed_p75_tokens_per_second": 355,
        "aa_speed_p95_tokens_per_second": 486,
        "aa_latency_seconds": 1.2,
        "aa_latency_first_token_seconds": 13.7,
        "aa_latency_p5_seconds": 0.65,
        "aa_latency_p25_seconds": 1.05,
        "aa_latency_p75_seconds": 2.37,
        "aa_latency_p95_seconds": 10.85,
        "aa_total_response_time_seconds": 16.44,
        "aa_reasoning_time_seconds": 12.5,
        "llmdex_adjusted_performance": 38,
        "llmdex_cost_index": 98.52,
        "llmdex_speed_index": 62.2,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61,
        "llmdex_efficiency_score": 56.67,
        "llmdex_performance_rank": 51,
        "llmdex_value_rank": 12,
        "llmdex_efficiency_rank": 28,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nemotron-cascade-2-30b-a3b:default",
        "family_id": "nvidia/nemotron-cascade-2-30b-a3b",
        "variant_id": "nvidia/nemotron-cascade-2-30b-a3b:default",
        "canonical_name": "Nemotron Cascade 2 30B A3B",
        "source_name": "Nemotron Cascade 2 30B A3B",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nemotron-cascade-2-30b-a3b",
        "source_model_url": "https://artificialanalysis.ai/models/nemotron-cascade-2-30b-a3b",
        "source_rank": 131,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 18,
        "aa_official_coding_index": 28,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 21,
        "aa_terminalbench_v21": 21,
        "aa_tau2": 53,
        "aa_tau3_banking": 10,
        "aa_lcr": 34,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 11,
        "aa_gpqa": 76,
        "aa_scicode": 35,
        "aa_ifbench": 80,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 18,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 18,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 131,
        "llmdex_value_rank": 197,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-3-nano-4b:default",
        "family_id": "nvidia/nvidia-nemotron-3-nano-4b",
        "variant_id": "nvidia/nvidia-nemotron-3-nano-4b:default",
        "canonical_name": "NVIDIA Nemotron 3 Nano 4B",
        "source_name": "NVIDIA Nemotron 3 Nano 4B",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nvidia-nemotron-3-nano-4b",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-4b",
        "source_rank": 192,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 10,
        "aa_omniscience_index": -72,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 7,
        "aa_terminalbench_v21": 4,
        "aa_tau2": 28,
        "aa_tau3_banking": 7,
        "aa_lcr": 17,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 5,
        "aa_gpqa": 51,
        "aa_scicode": 16,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 192,
        "llmdex_value_rank": 221,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-3-nano:default",
        "family_id": "nvidia/nvidia-nemotron-3-nano",
        "variant_id": "nvidia/nvidia-nemotron-3-nano:default",
        "canonical_name": "NVIDIA Nemotron 3 Nano",
        "source_name": "NVIDIA Nemotron 3 Nano",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "nvidia-nemotron-3-nano",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b",
        "source_rank": 203,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 23,
        "aa_omniscience_index": -69,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 12,
        "aa_terminalbench_v21": null,
        "aa_tau2": 25,
        "aa_tau3_banking": null,
        "aa_lcr": 7,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 5,
        "aa_gpqa": 40,
        "aa_scicode": 23,
        "aa_ifbench": 37,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.05,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.11,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 124,
        "aa_speed_p5_tokens_per_second": 49,
        "aa_speed_p25_tokens_per_second": 86,
        "aa_speed_p75_tokens_per_second": 226,
        "aa_speed_p95_tokens_per_second": 310,
        "aa_latency_seconds": 0.66,
        "aa_latency_first_token_seconds": 0.66,
        "aa_latency_p5_seconds": 0.33,
        "aa_latency_p25_seconds": 0.46,
        "aa_latency_p75_seconds": 1.13,
        "aa_latency_p95_seconds": 2.5,
        "aa_total_response_time_seconds": 4.69,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": 99.89,
        "llmdex_speed_index": 59.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 45.29,
        "llmdex_efficiency_score": 74.17,
        "llmdex_performance_rank": 203,
        "llmdex_value_rank": 137,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-3-nano:reasoning",
        "family_id": "nvidia/nvidia-nemotron-3-nano",
        "variant_id": "nvidia/nvidia-nemotron-3-nano:reasoning",
        "canonical_name": "NVIDIA Nemotron 3 Nano (reasoning)",
        "source_name": "NVIDIA Nemotron 3 Nano (reasoning)",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nvidia-nemotron-3-nano-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-nano-30b-a3b-reasoning",
        "source_rank": 152,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 18.5,
        "aa_omniscience_index": -52,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 14,
        "aa_terminalbench_v21": 7,
        "aa_tau2": 41,
        "aa_tau3_banking": 6,
        "aa_lcr": 34,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 17,
        "aa_hle": 10,
        "aa_gpqa": 76,
        "aa_scicode": 30,
        "aa_ifbench": 71,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.05,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.11,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 117,
        "aa_speed_p5_tokens_per_second": 35,
        "aa_speed_p25_tokens_per_second": 73,
        "aa_speed_p75_tokens_per_second": 222,
        "aa_speed_p95_tokens_per_second": 280,
        "aa_latency_seconds": 1.4,
        "aa_latency_first_token_seconds": 18.54,
        "aa_latency_p5_seconds": 0.95,
        "aa_latency_p25_seconds": 1.02,
        "aa_latency_p75_seconds": 8.09,
        "aa_latency_p95_seconds": 30.89,
        "aa_total_response_time_seconds": 22.82,
        "aa_reasoning_time_seconds": 17.14,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 99.89,
        "llmdex_speed_index": 54.7,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 47.91,
        "llmdex_efficiency_score": 83.89,
        "llmdex_performance_rank": 152,
        "llmdex_value_rank": 117,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-3-super:default",
        "family_id": "nvidia/nvidia-nemotron-3-super",
        "variant_id": "nvidia/nvidia-nemotron-3-super:default",
        "canonical_name": "NVIDIA Nemotron 3 Super",
        "source_name": "NVIDIA Nemotron 3 Super",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nvidia-nemotron-3-super",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-3-super-120b-a12b",
        "source_rank": 96,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 25,
        "aa_official_coding_index": 37.5,
        "aa_omniscience_index": -42,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 10,
        "aa_terminalbench_hard": 29,
        "aa_terminalbench_v21": 39,
        "aa_tau2": 68,
        "aa_tau3_banking": 10,
        "aa_lcr": 60,
        "aa_omniscience_accuracy": 24,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 19,
        "aa_gpqa": 80,
        "aa_scicode": 36,
        "aa_ifbench": 71,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 2,
        "aa_itbench": 1,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.25,
        "aa_output_cost_usd_per_1m": 0.78,
        "aa_blended_cost_usd_per_1m": 0.462,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 249,
        "aa_speed_p5_tokens_per_second": 121,
        "aa_speed_p25_tokens_per_second": 141,
        "aa_speed_p75_tokens_per_second": 363,
        "aa_speed_p95_tokens_per_second": 440,
        "aa_latency_seconds": 1.4,
        "aa_latency_first_token_seconds": 9.43,
        "aa_latency_p5_seconds": 0.91,
        "aa_latency_p25_seconds": 0.97,
        "aa_latency_p75_seconds": 1.74,
        "aa_latency_p95_seconds": 2.02,
        "aa_total_response_time_seconds": 11.43,
        "aa_reasoning_time_seconds": 8.02,
        "llmdex_adjusted_performance": 25,
        "llmdex_cost_index": 99.54,
        "llmdex_speed_index": 67.9,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.94,
        "llmdex_efficiency_score": 70,
        "llmdex_performance_rank": 96,
        "llmdex_value_rank": 56,
        "llmdex_efficiency_rank": 16,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-nano-12b-v2-vl:default",
        "family_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl",
        "variant_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl:default",
        "canonical_name": "NVIDIA Nemotron Nano 12B v2 VL",
        "source_name": "NVIDIA Nemotron Nano 12B v2 VL",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "nvidia-nemotron-nano-12b-v2-vl",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl",
        "source_rank": 226,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 5,
        "aa_official_coding_index": 18,
        "aa_omniscience_index": -73,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 19,
        "aa_tau3_banking": null,
        "aa_lcr": 17,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 4,
        "aa_gpqa": 44,
        "aa_scicode": 18,
        "aa_ifbench": 26,
        "aa_critpt": 0,
        "aa_mmmu_pro": 45,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.2,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.36,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 172,
        "aa_speed_p5_tokens_per_second": 32,
        "aa_speed_p25_tokens_per_second": 90,
        "aa_speed_p75_tokens_per_second": 204,
        "aa_speed_p95_tokens_per_second": 213,
        "aa_latency_seconds": 2.21,
        "aa_latency_first_token_seconds": 2.21,
        "aa_latency_p5_seconds": 1.09,
        "aa_latency_p25_seconds": 1.17,
        "aa_latency_p75_seconds": 6.55,
        "aa_latency_p95_seconds": 26.67,
        "aa_total_response_time_seconds": 5.12,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 5,
        "llmdex_cost_index": 99.64,
        "llmdex_speed_index": 56.15,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 43.62,
        "llmdex_efficiency_score": 36.67,
        "llmdex_performance_rank": 226,
        "llmdex_value_rank": 147,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-nano-12b-v2-vl:reasoning",
        "family_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl",
        "variant_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl:reasoning",
        "canonical_name": "NVIDIA Nemotron Nano 12B v2 VL (reasoning)",
        "source_name": "NVIDIA Nemotron Nano 12B v2 VL (reasoning)",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nvidia-nemotron-nano-12b-v2-vl-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-nano-12b-v2-vl-reasoning",
        "source_rank": 186,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 26,
        "aa_omniscience_index": -64,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 21,
        "aa_tau3_banking": null,
        "aa_lcr": 40,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 5,
        "aa_gpqa": 57,
        "aa_scicode": 26,
        "aa_ifbench": 32,
        "aa_critpt": 0,
        "aa_mmmu_pro": 53,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.2,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.36,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 65,
        "aa_speed_p5_tokens_per_second": 31,
        "aa_speed_p25_tokens_per_second": 49,
        "aa_speed_p75_tokens_per_second": 115,
        "aa_speed_p95_tokens_per_second": 178,
        "aa_latency_seconds": 5.53,
        "aa_latency_first_token_seconds": 36.24,
        "aa_latency_p5_seconds": 1.6,
        "aa_latency_p25_seconds": 2.13,
        "aa_latency_p75_seconds": 13.54,
        "aa_latency_p95_seconds": 28.25,
        "aa_total_response_time_seconds": 43.92,
        "aa_reasoning_time_seconds": 30.71,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.64,
        "llmdex_speed_index": 28.85,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 40.16,
        "llmdex_efficiency_score": 55,
        "llmdex_performance_rank": 186,
        "llmdex_value_rank": 172,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-nano-9b-v2:default",
        "family_id": "nvidia/nvidia-nemotron-nano-9b-v2",
        "variant_id": "nvidia/nvidia-nemotron-nano-9b-v2:default",
        "canonical_name": "NVIDIA Nemotron Nano 9B V2",
        "source_name": "NVIDIA Nemotron Nano 9B V2",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "nvidia-nemotron-nano-9b-v2",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2",
        "source_rank": 204,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 21,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 23,
        "aa_tau3_banking": null,
        "aa_lcr": 23,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 26,
        "aa_hle": 4,
        "aa_gpqa": 56,
        "aa_scicode": 21,
        "aa_ifbench": 27,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.05,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.11,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 155,
        "aa_speed_p5_tokens_per_second": 59,
        "aa_speed_p25_tokens_per_second": 89,
        "aa_speed_p75_tokens_per_second": 169,
        "aa_speed_p95_tokens_per_second": 178,
        "aa_latency_seconds": 1.66,
        "aa_latency_first_token_seconds": 1.66,
        "aa_latency_p5_seconds": 1.08,
        "aa_latency_p25_seconds": 1.15,
        "aa_latency_p75_seconds": 9.54,
        "aa_latency_p95_seconds": 20.36,
        "aa_total_response_time_seconds": 4.89,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": 99.89,
        "llmdex_speed_index": 57.2,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 44.91,
        "llmdex_efficiency_score": 74.17,
        "llmdex_performance_rank": 204,
        "llmdex_value_rank": 140,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "nvidia/nvidia-nemotron-nano-9b-v2:reasoning",
        "family_id": "nvidia/nvidia-nemotron-nano-9b-v2",
        "variant_id": "nvidia/nvidia-nemotron-nano-9b-v2:reasoning",
        "canonical_name": "NVIDIA Nemotron Nano 9B V2 (reasoning)",
        "source_name": "NVIDIA Nemotron Nano 9B V2 (reasoning)",
        "provider": "NVIDIA",
        "creator": "NVIDIA",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "nvidia-nemotron-nano-9b-v2-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/nvidia-nemotron-nano-9b-v2-reasoning",
        "source_rank": 190,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 22,
        "aa_omniscience_index": -43,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 22,
        "aa_tau3_banking": null,
        "aa_lcr": 21,
        "aa_omniscience_accuracy": 11,
        "aa_non_hallucination_rate": 39,
        "aa_hle": 5,
        "aa_gpqa": 57,
        "aa_scicode": 22,
        "aa_ifbench": 28,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.04,
        "aa_output_cost_usd_per_1m": 0.16,
        "aa_blended_cost_usd_per_1m": 0.088,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 86,
        "aa_speed_p5_tokens_per_second": 52,
        "aa_speed_p25_tokens_per_second": 74,
        "aa_speed_p75_tokens_per_second": 124,
        "aa_speed_p95_tokens_per_second": 144,
        "aa_latency_seconds": 7.34,
        "aa_latency_first_token_seconds": 30.69,
        "aa_latency_p5_seconds": 1.71,
        "aa_latency_p25_seconds": 3.95,
        "aa_latency_p75_seconds": 13.75,
        "aa_latency_p95_seconds": 31.73,
        "aa_total_response_time_seconds": 36.52,
        "aa_reasoning_time_seconds": 23.35,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": 99.91,
        "llmdex_speed_index": 21.9,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 38.85,
        "llmdex_efficiency_score": 81.11,
        "llmdex_performance_rank": 190,
        "llmdex_value_rank": 177,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-3-codex:xhigh",
        "family_id": "openai/gpt-5-3-codex",
        "variant_id": "openai/gpt-5-3-codex:xhigh",
        "canonical_name": "GPT-5.3 Codex (xhigh)",
        "source_name": "GPT-5.3 Codex (xhigh)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-3-codex-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-3-codex",
        "source_rank": 32,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 44,
        "aa_official_coding_index": 53,
        "aa_omniscience_index": 10,
        "aa_context_window_tokens": 400000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 53,
        "aa_terminalbench_v21": null,
        "aa_tau2": 86,
        "aa_tau3_banking": null,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 52,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 40,
        "aa_gpqa": 92,
        "aa_scicode": 53,
        "aa_ifbench": 75,
        "aa_critpt": 17,
        "aa_mmmu_pro": 78,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.75,
        "aa_output_cost_usd_per_1m": 14,
        "aa_blended_cost_usd_per_1m": 6.65,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 134,
        "aa_speed_p5_tokens_per_second": 84,
        "aa_speed_p25_tokens_per_second": 99,
        "aa_speed_p75_tokens_per_second": 152,
        "aa_speed_p95_tokens_per_second": 180,
        "aa_latency_seconds": 66.05,
        "aa_latency_first_token_seconds": 66.05,
        "aa_latency_p5_seconds": 36.06,
        "aa_latency_p25_seconds": 51.89,
        "aa_latency_p75_seconds": 88.28,
        "aa_latency_p95_seconds": 151.6,
        "aa_total_response_time_seconds": 69.79,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 44,
        "llmdex_cost_index": 93.35,
        "llmdex_speed_index": 13.4,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.68,
        "llmdex_efficiency_score": 19.44,
        "llmdex_performance_rank": 32,
        "llmdex_value_rank": 83,
        "llmdex_efficiency_rank": 67,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-5-instant-june-2026:default",
        "family_id": "openai/gpt-5-5-instant-june-2026",
        "variant_id": "openai/gpt-5-5-instant-june-2026:default",
        "canonical_name": "GPT-5.5 Instant (June 2026)",
        "source_name": "GPT-5.5 Instant (June 2026)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-5-instant-june-2026",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-5-instant-06-26",
        "source_rank": 83,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 29,
        "aa_official_coding_index": 42,
        "aa_omniscience_index": 3,
        "aa_context_window_tokens": 400000,
        "aa_gdpval": 11,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 35,
        "aa_tau2": null,
        "aa_tau3_banking": 12,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 44,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 19,
        "aa_gpqa": 82,
        "aa_scicode": 49,
        "aa_ifbench": null,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 29,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 50,
        "llmdex_efficiency_score": 2.78,
        "llmdex_performance_rank": 83,
        "llmdex_value_rank": 106,
        "llmdex_efficiency_rank": 88,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-5-pro:xhigh",
        "family_id": "openai/gpt-5-5-pro",
        "variant_id": "openai/gpt-5-5-pro:xhigh",
        "canonical_name": "GPT-5.5 Pro (xhigh)",
        "source_name": "GPT-5.5 Pro (xhigh)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-5-pro-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-5-pro",
        "source_rank": 262,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": null,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 922000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": 31,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": null,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 6.2,
        "llmdex_confidence_factor": 0.25,
        "llmdex_composite_index": null,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": null,
        "llmdex_value_rank": null,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 1
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:high",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:high",
        "canonical_name": "GPT-5.6 Luna (high)",
        "source_name": "GPT-5.6 Luna (high)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-luna-high",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna-high",
        "source_rank": 26,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 46,
        "aa_official_coding_index": 60.5,
        "aa_omniscience_index": -12,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 48,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 70,
        "aa_tau2": null,
        "aa_tau3_banking": 22,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 41,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 32,
        "aa_gpqa": 89,
        "aa_scicode": 51,
        "aa_ifbench": null,
        "aa_critpt": 17,
        "aa_mmmu_pro": 78,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 172,
        "aa_speed_p5_tokens_per_second": 134,
        "aa_speed_p25_tokens_per_second": 144,
        "aa_speed_p75_tokens_per_second": 200,
        "aa_speed_p95_tokens_per_second": 229,
        "aa_latency_seconds": 11.26,
        "aa_latency_first_token_seconds": 11.26,
        "aa_latency_p5_seconds": 4.37,
        "aa_latency_p25_seconds": 6.96,
        "aa_latency_p75_seconds": 26.41,
        "aa_latency_p95_seconds": 43.79,
        "aa_total_response_time_seconds": 14.16,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 46,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 17.2,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.54,
        "llmdex_efficiency_score": 41.67,
        "llmdex_performance_rank": 26,
        "llmdex_value_rank": 59,
        "llmdex_efficiency_rank": 44,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:low",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:low",
        "canonical_name": "GPT-5.6 Luna (low)",
        "source_name": "GPT-5.6 Luna (low)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-luna-low",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna-low",
        "source_rank": 69,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 33,
        "aa_official_coding_index": 44.5,
        "aa_omniscience_index": -15,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 33,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 43,
        "aa_tau2": null,
        "aa_tau3_banking": 12,
        "aa_lcr": 59,
        "aa_omniscience_accuracy": 39,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 19,
        "aa_gpqa": 84,
        "aa_scicode": 46,
        "aa_ifbench": null,
        "aa_critpt": 3,
        "aa_mmmu_pro": 74,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 160,
        "aa_speed_p5_tokens_per_second": 120,
        "aa_speed_p25_tokens_per_second": 141,
        "aa_speed_p75_tokens_per_second": 178,
        "aa_speed_p95_tokens_per_second": 230,
        "aa_latency_seconds": 1.55,
        "aa_latency_first_token_seconds": 1.55,
        "aa_latency_p5_seconds": 1.15,
        "aa_latency_p25_seconds": 1.29,
        "aa_latency_p75_seconds": 1.98,
        "aa_latency_p95_seconds": 3.73,
        "aa_total_response_time_seconds": 4.68,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 33,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 58.25,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.25,
        "llmdex_efficiency_score": 31.67,
        "llmdex_performance_rank": 69,
        "llmdex_value_rank": 36,
        "llmdex_efficiency_rank": 54,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:max",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:max",
        "canonical_name": "GPT-5.6 Luna (max)",
        "source_name": "GPT-5.6 Luna (max)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-6-luna-max",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna",
        "source_rank": 16,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 51,
        "aa_official_coding_index": 67,
        "aa_omniscience_index": -11,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 54,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 81,
        "aa_tau2": null,
        "aa_tau3_banking": 27,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 42,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 37,
        "aa_gpqa": 91,
        "aa_scicode": 53,
        "aa_ifbench": null,
        "aa_critpt": 21,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": 36,
        "aa_itbench": 40,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 188,
        "aa_speed_p5_tokens_per_second": 153,
        "aa_speed_p25_tokens_per_second": 164,
        "aa_speed_p75_tokens_per_second": 212,
        "aa_speed_p95_tokens_per_second": 302,
        "aa_latency_seconds": 139.35,
        "aa_latency_first_token_seconds": 139.35,
        "aa_latency_p5_seconds": 76.46,
        "aa_latency_p25_seconds": 104.87,
        "aa_latency_p75_seconds": 162.09,
        "aa_latency_p95_seconds": 231.43,
        "aa_total_response_time_seconds": 142,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 51,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 18.8,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.36,
        "llmdex_efficiency_score": 44.44,
        "llmdex_performance_rank": 16,
        "llmdex_value_rank": 26,
        "llmdex_efficiency_rank": 40,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:medium",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:medium",
        "canonical_name": "GPT-5.6 Luna (medium)",
        "source_name": "GPT-5.6 Luna (medium)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-luna-medium",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna-medium",
        "source_rank": 50,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 38,
        "aa_official_coding_index": 49.5,
        "aa_omniscience_index": -14,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 39,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 53,
        "aa_tau2": null,
        "aa_tau3_banking": 15,
        "aa_lcr": 66,
        "aa_omniscience_accuracy": 40,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 24,
        "aa_gpqa": 86,
        "aa_scicode": 46,
        "aa_ifbench": null,
        "aa_critpt": 5,
        "aa_mmmu_pro": 76,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 167,
        "aa_speed_p5_tokens_per_second": 122,
        "aa_speed_p25_tokens_per_second": 151,
        "aa_speed_p75_tokens_per_second": 219,
        "aa_speed_p95_tokens_per_second": 246,
        "aa_latency_seconds": 3.4,
        "aa_latency_first_token_seconds": 3.4,
        "aa_latency_p5_seconds": 1.53,
        "aa_latency_p25_seconds": 1.6,
        "aa_latency_p75_seconds": 3.98,
        "aa_latency_p95_seconds": 5.84,
        "aa_total_response_time_seconds": 6.39,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 38,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 49.7,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.04,
        "llmdex_efficiency_score": 33.89,
        "llmdex_performance_rank": 50,
        "llmdex_value_rank": 28,
        "llmdex_efficiency_rank": 51,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:non-reasoning",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:non-reasoning",
        "canonical_name": "GPT-5.6 Luna (Non-reasoning)",
        "source_name": "GPT-5.6 Luna (Non-reasoning)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-luna-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna-non-reasoning",
        "source_rank": 89,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 27,
        "aa_official_coding_index": 39.5,
        "aa_omniscience_index": -25,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 29,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 39,
        "aa_tau2": null,
        "aa_tau3_banking": 9,
        "aa_lcr": 36,
        "aa_omniscience_accuracy": 28,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 7,
        "aa_gpqa": 65,
        "aa_scicode": 40,
        "aa_ifbench": null,
        "aa_critpt": 0,
        "aa_mmmu_pro": 60,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 165,
        "aa_speed_p5_tokens_per_second": 134,
        "aa_speed_p25_tokens_per_second": 149,
        "aa_speed_p75_tokens_per_second": 214,
        "aa_speed_p95_tokens_per_second": 229,
        "aa_latency_seconds": 0.7,
        "aa_latency_first_token_seconds": 0.7,
        "aa_latency_p5_seconds": 0.54,
        "aa_latency_p25_seconds": 0.63,
        "aa_latency_p75_seconds": 0.81,
        "aa_latency_p95_seconds": 3.39,
        "aa_total_response_time_seconds": 3.72,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 27,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 63,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.2,
        "llmdex_efficiency_score": 26.67,
        "llmdex_performance_rank": 89,
        "llmdex_value_rank": 65,
        "llmdex_efficiency_rank": 58,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-luna:xhigh",
        "family_id": "openai/gpt-5-6-luna",
        "variant_id": "openai/gpt-5-6-luna:xhigh",
        "canonical_name": "GPT-5.6 Luna (xhigh)",
        "source_name": "GPT-5.6 Luna (xhigh)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-luna-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-luna-xhigh",
        "source_rank": 23,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 49,
        "aa_official_coding_index": 64,
        "aa_omniscience_index": -12,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 51,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 78,
        "aa_tau2": null,
        "aa_tau3_banking": 24,
        "aa_lcr": 70,
        "aa_omniscience_accuracy": 41,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 36,
        "aa_gpqa": 89,
        "aa_scicode": 50,
        "aa_ifbench": null,
        "aa_critpt": 21,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 168,
        "aa_speed_p5_tokens_per_second": 127,
        "aa_speed_p25_tokens_per_second": 142,
        "aa_speed_p75_tokens_per_second": 202,
        "aa_speed_p95_tokens_per_second": 238,
        "aa_latency_seconds": 40.36,
        "aa_latency_first_token_seconds": 40.36,
        "aa_latency_p5_seconds": 18.58,
        "aa_latency_p25_seconds": 23.73,
        "aa_latency_p75_seconds": 81.47,
        "aa_latency_p95_seconds": 100.46,
        "aa_total_response_time_seconds": 43.34,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 49,
        "llmdex_cost_index": 97,
        "llmdex_speed_index": 16.8,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.96,
        "llmdex_efficiency_score": 43.33,
        "llmdex_performance_rank": 23,
        "llmdex_value_rank": 40,
        "llmdex_efficiency_rank": 42,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:high",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:high",
        "canonical_name": "GPT-5.6 Sol (high)",
        "source_name": "GPT-5.6 Sol (high)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-sol-high",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol-high",
        "source_rank": 9,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 56,
        "aa_official_coding_index": 72,
        "aa_omniscience_index": 20,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 56,
        "aa_terminalbench_hard": 62,
        "aa_terminalbench_v21": 87,
        "aa_tau2": 83,
        "aa_tau3_banking": 31,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 57,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 44,
        "aa_gpqa": 93,
        "aa_scicode": 57,
        "aa_ifbench": 69,
        "aa_critpt": 26,
        "aa_mmmu_pro": 82,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 63,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 54,
        "aa_speed_p75_tokens_per_second": 82,
        "aa_speed_p95_tokens_per_second": 109,
        "aa_latency_seconds": 21.85,
        "aa_latency_first_token_seconds": 21.85,
        "aa_latency_p5_seconds": 5.12,
        "aa_latency_p25_seconds": 6.63,
        "aa_latency_p75_seconds": 53.53,
        "aa_latency_p95_seconds": 71.72,
        "aa_total_response_time_seconds": 29.75,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 56,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 6.3,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 54.76,
        "llmdex_efficiency_score": 7.78,
        "llmdex_performance_rank": 9,
        "llmdex_value_rank": 68,
        "llmdex_efficiency_rank": 82,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:low",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:low",
        "canonical_name": "GPT-5.6 Sol (low)",
        "source_name": "GPT-5.6 Sol (low)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-sol-low",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol-low",
        "source_rank": 22,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 49,
        "aa_official_coding_index": 66,
        "aa_omniscience_index": 18,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 47,
        "aa_terminalbench_hard": 61,
        "aa_terminalbench_v21": 77,
        "aa_tau2": 76,
        "aa_tau3_banking": 24,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 56,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 37,
        "aa_gpqa": 90,
        "aa_scicode": 55,
        "aa_ifbench": 67,
        "aa_critpt": 15,
        "aa_mmmu_pro": 81,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 58,
        "aa_speed_p5_tokens_per_second": 43,
        "aa_speed_p25_tokens_per_second": 49,
        "aa_speed_p75_tokens_per_second": 80,
        "aa_speed_p95_tokens_per_second": 119,
        "aa_latency_seconds": 2.97,
        "aa_latency_first_token_seconds": 2.97,
        "aa_latency_p5_seconds": 1.56,
        "aa_latency_p25_seconds": 2.19,
        "aa_latency_p75_seconds": 4.03,
        "aa_latency_p95_seconds": 9.39,
        "aa_total_response_time_seconds": 11.55,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 49,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 40.95,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.19,
        "llmdex_efficiency_score": 6.11,
        "llmdex_performance_rank": 22,
        "llmdex_value_rank": 27,
        "llmdex_efficiency_rank": 85,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:max",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:max",
        "canonical_name": "GPT-5.6 Sol (max)",
        "source_name": "GPT-5.6 Sol (max)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-6-sol-max",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol",
        "source_rank": 4,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 59,
        "aa_official_coding_index": 72,
        "aa_omniscience_index": 22,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 62,
        "aa_terminalbench_hard": 66,
        "aa_terminalbench_v21": 88,
        "aa_tau2": 85,
        "aa_tau3_banking": 33,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 59,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 47,
        "aa_gpqa": 94,
        "aa_scicode": 56,
        "aa_ifbench": 73,
        "aa_critpt": 32,
        "aa_mmmu_pro": 83,
        "aa_apex_agents": null,
        "aa_itbench": 56,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 66,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 57,
        "aa_speed_p75_tokens_per_second": 85,
        "aa_speed_p95_tokens_per_second": 114,
        "aa_latency_seconds": 144.56,
        "aa_latency_first_token_seconds": 144.56,
        "aa_latency_p5_seconds": 51.18,
        "aa_latency_p25_seconds": 72.42,
        "aa_latency_p75_seconds": 288.6,
        "aa_latency_p95_seconds": 474.33,
        "aa_total_response_time_seconds": 152.15,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 59,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 6.6,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.32,
        "llmdex_efficiency_score": 9.44,
        "llmdex_performance_rank": 4,
        "llmdex_value_rank": 49,
        "llmdex_efficiency_rank": 79,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:medium",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:medium",
        "canonical_name": "GPT-5.6 Sol (medium)",
        "source_name": "GPT-5.6 Sol (medium)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-sol-medium",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol-medium",
        "source_rank": 13,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 54,
        "aa_official_coding_index": 71,
        "aa_omniscience_index": 19,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 53,
        "aa_terminalbench_hard": 63,
        "aa_terminalbench_v21": 86,
        "aa_tau2": 81,
        "aa_tau3_banking": 26,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 57,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 40,
        "aa_gpqa": 93,
        "aa_scicode": 56,
        "aa_ifbench": 70,
        "aa_critpt": 23,
        "aa_mmmu_pro": 81,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 64,
        "aa_speed_p5_tokens_per_second": 46,
        "aa_speed_p25_tokens_per_second": 50,
        "aa_speed_p75_tokens_per_second": 80,
        "aa_speed_p95_tokens_per_second": 106,
        "aa_latency_seconds": 5.08,
        "aa_latency_first_token_seconds": 5.08,
        "aa_latency_p5_seconds": 2.44,
        "aa_latency_p25_seconds": 3.2,
        "aa_latency_p75_seconds": 25.49,
        "aa_latency_p95_seconds": 34.99,
        "aa_total_response_time_seconds": 12.9,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 54,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 31,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.7,
        "llmdex_efficiency_score": 7.22,
        "llmdex_performance_rank": 13,
        "llmdex_value_rank": 20,
        "llmdex_efficiency_rank": 83,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:non-reasoning",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:non-reasoning",
        "canonical_name": "GPT-5.6 Sol (Non-reasoning)",
        "source_name": "GPT-5.6 Sol (Non-reasoning)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-sol-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol-non-reasoning",
        "source_rank": 41,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 41,
        "aa_official_coding_index": 60.5,
        "aa_omniscience_index": 1,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 44,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 74,
        "aa_tau2": null,
        "aa_tau3_banking": 16,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 48,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 16,
        "aa_gpqa": 79,
        "aa_scicode": 47,
        "aa_ifbench": null,
        "aa_critpt": 5,
        "aa_mmmu_pro": 72,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 65,
        "aa_speed_p5_tokens_per_second": 41,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 82,
        "aa_speed_p95_tokens_per_second": 102,
        "aa_latency_seconds": 0.99,
        "aa_latency_first_token_seconds": 0.99,
        "aa_latency_p5_seconds": 0.83,
        "aa_latency_p25_seconds": 0.9,
        "aa_latency_p75_seconds": 1.08,
        "aa_latency_p95_seconds": 1.6,
        "aa_total_response_time_seconds": 8.65,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 41,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 51.55,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.31,
        "llmdex_efficiency_score": 4.44,
        "llmdex_performance_rank": 41,
        "llmdex_value_rank": 50,
        "llmdex_efficiency_rank": 86,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-sol:xhigh",
        "family_id": "openai/gpt-5-6-sol",
        "variant_id": "openai/gpt-5-6-sol:xhigh",
        "canonical_name": "GPT-5.6 Sol (xhigh)",
        "source_name": "GPT-5.6 Sol (xhigh)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-sol-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-sol-xhigh",
        "source_rank": 6,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 58,
        "aa_official_coding_index": 73,
        "aa_omniscience_index": 21,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 60,
        "aa_terminalbench_hard": 61,
        "aa_terminalbench_v21": 90,
        "aa_tau2": 85,
        "aa_tau3_banking": 33,
        "aa_lcr": 71,
        "aa_omniscience_accuracy": 58,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 45,
        "aa_gpqa": 93,
        "aa_scicode": 56,
        "aa_ifbench": 71,
        "aa_critpt": 29,
        "aa_mmmu_pro": 83,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 5,
        "aa_output_cost_usd_per_1m": 30,
        "aa_blended_cost_usd_per_1m": 15,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 70,
        "aa_speed_p5_tokens_per_second": 47,
        "aa_speed_p25_tokens_per_second": 53,
        "aa_speed_p75_tokens_per_second": 83,
        "aa_speed_p95_tokens_per_second": 115,
        "aa_latency_seconds": 51.95,
        "aa_latency_first_token_seconds": 51.95,
        "aa_latency_p5_seconds": 15.06,
        "aa_latency_p25_seconds": 28.4,
        "aa_latency_p75_seconds": 134.05,
        "aa_latency_p95_seconds": 216.86,
        "aa_total_response_time_seconds": 59.11,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 58,
        "llmdex_cost_index": 85,
        "llmdex_speed_index": 7,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 55.9,
        "llmdex_efficiency_score": 8.33,
        "llmdex_performance_rank": 6,
        "llmdex_value_rank": 57,
        "llmdex_efficiency_rank": 81,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:high",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:high",
        "canonical_name": "GPT-5.6 Terra (high)",
        "source_name": "GPT-5.6 Terra (high)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-terra-high",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra-high",
        "source_rank": 24,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 49,
        "aa_official_coding_index": 63,
        "aa_omniscience_index": -4,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 50,
        "aa_terminalbench_hard": 58,
        "aa_terminalbench_v21": 76,
        "aa_tau2": 78,
        "aa_tau3_banking": 22,
        "aa_lcr": 72,
        "aa_omniscience_accuracy": 44,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 37,
        "aa_gpqa": 90,
        "aa_scicode": 50,
        "aa_ifbench": 64,
        "aa_critpt": 23,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 122,
        "aa_speed_p5_tokens_per_second": 86,
        "aa_speed_p25_tokens_per_second": 99,
        "aa_speed_p75_tokens_per_second": 143,
        "aa_speed_p95_tokens_per_second": 189,
        "aa_latency_seconds": 3.3,
        "aa_latency_first_token_seconds": 3.3,
        "aa_latency_p5_seconds": 1.39,
        "aa_latency_p25_seconds": 1.71,
        "aa_latency_p75_seconds": 15.34,
        "aa_latency_p95_seconds": 39.3,
        "aa_total_response_time_seconds": 7.39,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 49,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 45.7,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.39,
        "llmdex_efficiency_score": 18.89,
        "llmdex_performance_rank": 24,
        "llmdex_value_rank": 7,
        "llmdex_efficiency_rank": 68,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:low",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:low",
        "canonical_name": "GPT-5.6 Terra (low)",
        "source_name": "GPT-5.6 Terra (low)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-terra-low",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra-low",
        "source_rank": 44,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 40,
        "aa_official_coding_index": 56,
        "aa_omniscience_index": -7,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 38,
        "aa_terminalbench_hard": 44,
        "aa_terminalbench_v21": 63,
        "aa_tau2": 61,
        "aa_tau3_banking": 16,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 43,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 27,
        "aa_gpqa": 84,
        "aa_scicode": 49,
        "aa_ifbench": 60,
        "aa_critpt": 9,
        "aa_mmmu_pro": 76,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 113,
        "aa_speed_p5_tokens_per_second": 84,
        "aa_speed_p25_tokens_per_second": 91,
        "aa_speed_p75_tokens_per_second": 141,
        "aa_speed_p95_tokens_per_second": 174,
        "aa_latency_seconds": 1.49,
        "aa_latency_first_token_seconds": 1.49,
        "aa_latency_p5_seconds": 1.01,
        "aa_latency_p25_seconds": 1.27,
        "aa_latency_p75_seconds": 2.42,
        "aa_latency_p95_seconds": 6.13,
        "aa_total_response_time_seconds": 5.94,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 40,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 53.85,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.52,
        "llmdex_efficiency_score": 16.11,
        "llmdex_performance_rank": 44,
        "llmdex_value_rank": 23,
        "llmdex_efficiency_rank": 71,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:max",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:max",
        "canonical_name": "GPT-5.6 Terra (max)",
        "source_name": "GPT-5.6 Terra (max)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "gpt-5-6-terra-max",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra",
        "source_rank": 11,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 55,
        "aa_official_coding_index": 71,
        "aa_omniscience_index": 0,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 54,
        "aa_terminalbench_hard": 58,
        "aa_terminalbench_v21": 88,
        "aa_tau2": 86,
        "aa_tau3_banking": 32,
        "aa_lcr": 74,
        "aa_omniscience_accuracy": 46,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 42,
        "aa_gpqa": 93,
        "aa_scicode": 54,
        "aa_ifbench": 71,
        "aa_critpt": 30,
        "aa_mmmu_pro": 81,
        "aa_apex_agents": 39,
        "aa_itbench": 51,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 136,
        "aa_speed_p5_tokens_per_second": 97,
        "aa_speed_p25_tokens_per_second": 121,
        "aa_speed_p75_tokens_per_second": 173,
        "aa_speed_p95_tokens_per_second": 229,
        "aa_latency_seconds": 178.38,
        "aa_latency_first_token_seconds": 178.38,
        "aa_latency_p5_seconds": 94.19,
        "aa_latency_p25_seconds": 103.18,
        "aa_latency_p75_seconds": 214.93,
        "aa_latency_p95_seconds": 269.3,
        "aa_total_response_time_seconds": 182.06,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 55,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 13.6,
        "llmdex_coverage_score": 93.8,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.97,
        "llmdex_efficiency_score": 22.78,
        "llmdex_performance_rank": 11,
        "llmdex_value_rank": 30,
        "llmdex_efficiency_rank": 63,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:medium",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:medium",
        "canonical_name": "GPT-5.6 Terra (medium)",
        "source_name": "GPT-5.6 Terra (medium)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-terra-medium",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra-medium",
        "source_rank": 28,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 46,
        "aa_official_coding_index": 61,
        "aa_omniscience_index": -5,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 45,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 72,
        "aa_tau2": 73,
        "aa_tau3_banking": 19,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 44,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 32,
        "aa_gpqa": 87,
        "aa_scicode": 50,
        "aa_ifbench": 62,
        "aa_critpt": 17,
        "aa_mmmu_pro": 77,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 117,
        "aa_speed_p5_tokens_per_second": 86,
        "aa_speed_p25_tokens_per_second": 94,
        "aa_speed_p75_tokens_per_second": 139,
        "aa_speed_p95_tokens_per_second": 179,
        "aa_latency_seconds": 1.92,
        "aa_latency_first_token_seconds": 1.92,
        "aa_latency_p5_seconds": 1.1,
        "aa_latency_p25_seconds": 1.5,
        "aa_latency_p75_seconds": 2.77,
        "aa_latency_p95_seconds": 7.1,
        "aa_total_response_time_seconds": 6.19,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 46,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 52.1,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.17,
        "llmdex_efficiency_score": 17.78,
        "llmdex_performance_rank": 28,
        "llmdex_value_rank": 9,
        "llmdex_efficiency_rank": 69,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:non-reasoning",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:non-reasoning",
        "canonical_name": "GPT-5.6 Terra (Non-reasoning)",
        "source_name": "GPT-5.6 Terra (Non-reasoning)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-terra-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra-non-reasoning",
        "source_rank": 64,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 50.5,
        "aa_omniscience_index": -23,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 37,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 56,
        "aa_tau2": null,
        "aa_tau3_banking": 13,
        "aa_lcr": 50,
        "aa_omniscience_accuracy": 36,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 11,
        "aa_gpqa": 75,
        "aa_scicode": 45,
        "aa_ifbench": null,
        "aa_critpt": 2,
        "aa_mmmu_pro": 67,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 107,
        "aa_speed_p5_tokens_per_second": 81,
        "aa_speed_p25_tokens_per_second": 95,
        "aa_speed_p75_tokens_per_second": 145,
        "aa_speed_p95_tokens_per_second": 171,
        "aa_latency_seconds": 0.75,
        "aa_latency_first_token_seconds": 0.75,
        "aa_latency_p5_seconds": 0.64,
        "aa_latency_p25_seconds": 0.66,
        "aa_latency_p75_seconds": 0.86,
        "aa_latency_p95_seconds": 1.04,
        "aa_total_response_time_seconds": 5.41,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 56.95,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.14,
        "llmdex_efficiency_score": 12.22,
        "llmdex_performance_rank": 64,
        "llmdex_value_rank": 54,
        "llmdex_efficiency_rank": 75,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-5-6-terra:xhigh",
        "family_id": "openai/gpt-5-6-terra",
        "variant_id": "openai/gpt-5-6-terra:xhigh",
        "canonical_name": "GPT-5.6 Terra (xhigh)",
        "source_name": "GPT-5.6 Terra (xhigh)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "gpt-5-6-terra-xhigh",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-5-6-terra-xhigh",
        "source_rank": 15,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 52,
        "aa_official_coding_index": 66,
        "aa_omniscience_index": -3,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 54,
        "aa_terminalbench_hard": 63,
        "aa_terminalbench_v21": 80,
        "aa_tau2": 80,
        "aa_tau3_banking": 24,
        "aa_lcr": 71,
        "aa_omniscience_accuracy": 45,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 40,
        "aa_gpqa": 91,
        "aa_scicode": 52,
        "aa_ifbench": 66,
        "aa_critpt": 27,
        "aa_mmmu_pro": 79,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2.5,
        "aa_output_cost_usd_per_1m": 15,
        "aa_blended_cost_usd_per_1m": 7.5,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 120,
        "aa_speed_p5_tokens_per_second": 88,
        "aa_speed_p25_tokens_per_second": 104,
        "aa_speed_p75_tokens_per_second": 142,
        "aa_speed_p95_tokens_per_second": 199,
        "aa_latency_seconds": 21.66,
        "aa_latency_first_token_seconds": 21.66,
        "aa_latency_p5_seconds": 3.15,
        "aa_latency_p25_seconds": 8.28,
        "aa_latency_p75_seconds": 58,
        "aa_latency_p95_seconds": 84.33,
        "aa_total_response_time_seconds": 25.82,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 52,
        "llmdex_cost_index": 92.5,
        "llmdex_speed_index": 12,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.15,
        "llmdex_efficiency_score": 21.11,
        "llmdex_performance_rank": 15,
        "llmdex_value_rank": 53,
        "llmdex_efficiency_rank": 65,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-oss-120b:high",
        "family_id": "openai/gpt-oss-120b",
        "variant_id": "openai/gpt-oss-120b:high",
        "canonical_name": "gpt-oss-120b (high)",
        "source_name": "gpt-oss-120b (high)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gpt-oss-120b-high",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-oss-120b",
        "source_rank": 102,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 24,
        "aa_official_coding_index": 32.5,
        "aa_omniscience_index": -50,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 15,
        "aa_terminalbench_hard": 23,
        "aa_terminalbench_v21": 26,
        "aa_tau2": 66,
        "aa_tau3_banking": 12,
        "aa_lcr": 51,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 18,
        "aa_gpqa": 78,
        "aa_scicode": 39,
        "aa_ifbench": 69,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 3,
        "aa_itbench": 6,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.15,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.33,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 273,
        "aa_speed_p5_tokens_per_second": 50,
        "aa_speed_p25_tokens_per_second": 120,
        "aa_speed_p75_tokens_per_second": 461,
        "aa_speed_p95_tokens_per_second": 1506,
        "aa_latency_seconds": 0.88,
        "aa_latency_first_token_seconds": 8.19,
        "aa_latency_p5_seconds": 0.38,
        "aa_latency_p25_seconds": 0.61,
        "aa_latency_p75_seconds": 1.19,
        "aa_latency_p95_seconds": 4.2,
        "aa_total_response_time_seconds": 10.02,
        "aa_reasoning_time_seconds": 7.32,
        "llmdex_adjusted_performance": 24,
        "llmdex_cost_index": 99.67,
        "llmdex_speed_index": 72.9,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.48,
        "llmdex_efficiency_score": 77.78,
        "llmdex_performance_rank": 102,
        "llmdex_value_rank": 46,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-oss-120b:low",
        "family_id": "openai/gpt-oss-120b",
        "variant_id": "openai/gpt-oss-120b:low",
        "canonical_name": "gpt-oss-120b (low)",
        "source_name": "gpt-oss-120b (low)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gpt-oss-120b-low",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-oss-120b-low",
        "source_rank": 146,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 15,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -50,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": 14,
        "aa_tau2": 45,
        "aa_tau3_banking": 3,
        "aa_lcr": 44,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 22,
        "aa_hle": 5,
        "aa_gpqa": 67,
        "aa_scicode": 36,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.15,
        "aa_output_cost_usd_per_1m": 0.6,
        "aa_blended_cost_usd_per_1m": 0.33,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 304,
        "aa_speed_p5_tokens_per_second": 51,
        "aa_speed_p25_tokens_per_second": 127,
        "aa_speed_p75_tokens_per_second": 483,
        "aa_speed_p95_tokens_per_second": 1640,
        "aa_latency_seconds": 0.9,
        "aa_latency_first_token_seconds": 7.48,
        "aa_latency_p5_seconds": 0.38,
        "aa_latency_p25_seconds": 0.64,
        "aa_latency_p75_seconds": 1.21,
        "aa_latency_p95_seconds": 5.26,
        "aa_total_response_time_seconds": 9.12,
        "aa_reasoning_time_seconds": 6.58,
        "llmdex_adjusted_performance": 15,
        "llmdex_cost_index": 99.67,
        "llmdex_speed_index": 75.9,
        "llmdex_coverage_score": 84.4,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.58,
        "llmdex_efficiency_score": 66.11,
        "llmdex_performance_rank": 146,
        "llmdex_value_rank": 86,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-oss-20b:high",
        "family_id": "openai/gpt-oss-20b",
        "variant_id": "openai/gpt-oss-20b:high",
        "canonical_name": "gpt-oss-20b (high)",
        "source_name": "gpt-oss-20b (high)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "gpt-oss-20b-high",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-oss-20b",
        "source_rank": 147,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 15,
        "aa_official_coding_index": 24,
        "aa_omniscience_index": -64,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": 3,
        "aa_terminalbench_hard": 11,
        "aa_terminalbench_v21": 14,
        "aa_tau2": 60,
        "aa_tau3_banking": 7,
        "aa_lcr": 31,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 10,
        "aa_gpqa": 69,
        "aa_scicode": 34,
        "aa_ifbench": 65,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 1,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.06,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.116,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 219,
        "aa_speed_p5_tokens_per_second": 75,
        "aa_speed_p25_tokens_per_second": 132,
        "aa_speed_p75_tokens_per_second": 327,
        "aa_speed_p95_tokens_per_second": 877,
        "aa_latency_seconds": 0.91,
        "aa_latency_first_token_seconds": 10.06,
        "aa_latency_p5_seconds": 0.31,
        "aa_latency_p25_seconds": 0.5,
        "aa_latency_p75_seconds": 1.25,
        "aa_latency_p95_seconds": 41.15,
        "aa_total_response_time_seconds": 12.34,
        "aa_reasoning_time_seconds": 9.15,
        "llmdex_adjusted_performance": 15,
        "llmdex_cost_index": 99.88,
        "llmdex_speed_index": 67.35,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.93,
        "llmdex_efficiency_score": 85,
        "llmdex_performance_rank": 147,
        "llmdex_value_rank": 97,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/gpt-oss-20b:low",
        "family_id": "openai/gpt-oss-20b",
        "variant_id": "openai/gpt-oss-20b:low",
        "canonical_name": "gpt-oss-20b (low)",
        "source_name": "gpt-oss-20b (low)",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "gpt-oss-20b-low",
        "source_model_url": "https://artificialanalysis.ai/models/gpt-oss-20b-low",
        "source_rank": 149,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 34,
        "aa_omniscience_index": -60,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 50,
        "aa_tau3_banking": null,
        "aa_lcr": 31,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 5,
        "aa_gpqa": 61,
        "aa_scicode": 34,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.07,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.122,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 227,
        "aa_speed_p5_tokens_per_second": 68,
        "aa_speed_p25_tokens_per_second": 147,
        "aa_speed_p75_tokens_per_second": 341,
        "aa_speed_p95_tokens_per_second": 929,
        "aa_latency_seconds": 0.85,
        "aa_latency_first_token_seconds": 9.68,
        "aa_latency_p5_seconds": 0.33,
        "aa_latency_p25_seconds": 0.59,
        "aa_latency_p75_seconds": 1.33,
        "aa_latency_p95_seconds": 16.74,
        "aa_total_response_time_seconds": 11.89,
        "aa_reasoning_time_seconds": 8.83,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": 99.88,
        "llmdex_speed_index": 68.45,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.65,
        "llmdex_efficiency_score": 82.78,
        "llmdex_performance_rank": 149,
        "llmdex_value_rank": 101,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openai/o3:default",
        "family_id": "openai/o3",
        "variant_id": "openai/o3:default",
        "canonical_name": "o3",
        "source_name": "o3",
        "provider": "OpenAI",
        "creator": "OpenAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "o3",
        "source_model_url": "https://artificialanalysis.ai/models/o3",
        "source_rank": 78,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 30,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -15,
        "aa_context_window_tokens": 200000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 37,
        "aa_terminalbench_v21": null,
        "aa_tau2": 81,
        "aa_tau3_banking": null,
        "aa_lcr": 69,
        "aa_omniscience_accuracy": 38,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 20,
        "aa_gpqa": 83,
        "aa_scicode": 41,
        "aa_ifbench": 71,
        "aa_critpt": 1,
        "aa_mmmu_pro": 70,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 8,
        "aa_blended_cost_usd_per_1m": 4.4,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 138,
        "aa_speed_p5_tokens_per_second": 80,
        "aa_speed_p25_tokens_per_second": 104,
        "aa_speed_p75_tokens_per_second": 158,
        "aa_speed_p95_tokens_per_second": 219,
        "aa_latency_seconds": 5.73,
        "aa_latency_first_token_seconds": 5.73,
        "aa_latency_p5_seconds": 2.46,
        "aa_latency_p25_seconds": 4.25,
        "aa_latency_p75_seconds": 8.81,
        "aa_latency_p95_seconds": 18.07,
        "aa_total_response_time_seconds": 9.37,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 30,
        "llmdex_cost_index": 95.6,
        "llmdex_speed_index": 35.15,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 50.71,
        "llmdex_efficiency_score": 20.56,
        "llmdex_performance_rank": 78,
        "llmdex_value_rank": 100,
        "llmdex_efficiency_rank": 66,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openbmb/minicpm-v-4-6-1-3b:default",
        "family_id": "openbmb/minicpm-v-4-6-1-3b",
        "variant_id": "openbmb/minicpm-v-4-6-1-3b:default",
        "canonical_name": "MiniCPM-V 4.6 1.3B",
        "source_name": "MiniCPM-V 4.6 1.3B",
        "provider": "OpenBMB",
        "creator": "OpenBMB",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "minicpm-v-4-6-1-3b",
        "source_model_url": "https://artificialanalysis.ai/models/minicpm-v4-6-1-3b",
        "source_rank": 228,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 1,
        "aa_omniscience_index": -85,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": 0,
        "aa_tau2": 88,
        "aa_tau3_banking": 4,
        "aa_lcr": 6,
        "aa_omniscience_accuracy": 6,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 5,
        "aa_gpqa": 31,
        "aa_scicode": 2,
        "aa_ifbench": 27,
        "aa_critpt": 0,
        "aa_mmmu_pro": 38,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 56.2,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 4,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 228,
        "llmdex_value_rank": 237,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openbmb/minicpm5-1b:default",
        "family_id": "openbmb/minicpm5-1b",
        "variant_id": "openbmb/minicpm5-1b:default",
        "canonical_name": "MiniCPM5-1B",
        "source_name": "MiniCPM5-1B",
        "provider": "OpenBMB",
        "creator": "OpenBMB",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "minicpm5-1b",
        "source_model_url": "https://artificialanalysis.ai/models/minicpm5-1b",
        "source_rank": 165,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": -17,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 81,
        "aa_tau3_banking": null,
        "aa_lcr": 4,
        "aa_omniscience_accuracy": 2,
        "aa_non_hallucination_rate": 81,
        "aa_hle": 7,
        "aa_gpqa": 28,
        "aa_scicode": 4,
        "aa_ifbench": 49,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 12,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 165,
        "llmdex_value_rank": 211,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "openbmb/minicpm5-1b:non-reasoning",
        "family_id": "openbmb/minicpm5-1b",
        "variant_id": "openbmb/minicpm5-1b:non-reasoning",
        "canonical_name": "MiniCPM5-1B (non-reasoning)",
        "source_name": "MiniCPM5-1B (non-reasoning)",
        "provider": "OpenBMB",
        "creator": "OpenBMB",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "minicpm5-1b-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/minicpm5-1b-non-reasoning",
        "source_rank": 169,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 1,
        "aa_omniscience_index": -1,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 82,
        "aa_tau3_banking": null,
        "aa_lcr": 5,
        "aa_omniscience_accuracy": 0,
        "aa_non_hallucination_rate": 99,
        "aa_hle": 5,
        "aa_gpqa": 27,
        "aa_scicode": 1,
        "aa_ifbench": 35,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 12,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 169,
        "llmdex_value_rank": 212,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "perplexity/r1-1776:default",
        "family_id": "perplexity/r1-1776",
        "variant_id": "perplexity/r1-1776:default",
        "canonical_name": "R1 1776",
        "source_name": "R1 1776",
        "provider": "Perplexity",
        "creator": "Perplexity",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "r1-1776",
        "source_model_url": "https://artificialanalysis.ai/models/r1-1776",
        "source_rank": 212,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 6,
        "aa_official_coding_index": null,
        "aa_omniscience_index": null,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": null,
        "aa_tau2": null,
        "aa_tau3_banking": null,
        "aa_lcr": null,
        "aa_omniscience_accuracy": null,
        "aa_non_hallucination_rate": null,
        "aa_hle": null,
        "aa_gpqa": null,
        "aa_scicode": null,
        "aa_ifbench": null,
        "aa_critpt": null,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 6,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 6.2,
        "llmdex_confidence_factor": 0.25,
        "llmdex_composite_index": 6,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 212,
        "llmdex_value_rank": 231,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 1
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "prime-intellect/intellect-3:default",
        "family_id": "prime-intellect/intellect-3",
        "variant_id": "prime-intellect/intellect-3:default",
        "canonical_name": "INTELLECT-3",
        "source_name": "INTELLECT-3",
        "provider": "Prime Intellect",
        "creator": "Prime Intellect",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "intellect-3",
        "source_model_url": "https://artificialanalysis.ai/models/intellect-3",
        "source_rank": 143,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 16,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -51,
        "aa_context_window_tokens": 131000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 9,
        "aa_terminalbench_v21": null,
        "aa_tau2": 27,
        "aa_tau3_banking": null,
        "aa_lcr": 32,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 12,
        "aa_gpqa": 76,
        "aa_scicode": 39,
        "aa_ifbench": 34,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 16,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 16,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 143,
        "llmdex_value_rank": 202,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "reka-ai/reka-flash-3:default",
        "family_id": "reka-ai/reka-flash-3",
        "variant_id": "reka-ai/reka-flash-3:default",
        "canonical_name": "Reka Flash 3",
        "source_name": "Reka Flash 3",
        "provider": "Reka AI",
        "creator": "Reka AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "reka-flash-3",
        "source_model_url": "https://artificialanalysis.ai/models/reka-flash-3",
        "source_rank": 230,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 4,
        "aa_official_coding_index": 27,
        "aa_omniscience_index": -65,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 0,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 10,
        "aa_hle": 5,
        "aa_gpqa": 53,
        "aa_scicode": 27,
        "aa_ifbench": 30,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.2,
        "aa_output_cost_usd_per_1m": 0.8,
        "aa_blended_cost_usd_per_1m": 0.44,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 4,
        "llmdex_cost_index": 99.56,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 39.83,
        "llmdex_efficiency_score": 27.22,
        "llmdex_performance_rank": 230,
        "llmdex_value_rank": 173,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "sapiens-ai/agnes-2-5-pro-alpha:default",
        "family_id": "sapiens-ai/agnes-2-5-pro-alpha",
        "variant_id": "sapiens-ai/agnes-2-5-pro-alpha:default",
        "canonical_name": "Agnes 2.5 Pro Alpha",
        "source_name": "Agnes 2.5 Pro Alpha",
        "provider": "Sapiens AI",
        "creator": "Sapiens AI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "agnes-2-5-pro-alpha",
        "source_model_url": "https://artificialanalysis.ai/models/agnes-2-5-pro-alpha",
        "source_rank": 49,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 39,
        "aa_official_coding_index": 54.5,
        "aa_omniscience_index": -26,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 33,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 67,
        "aa_tau2": null,
        "aa_tau3_banking": 12,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 32,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 32,
        "aa_gpqa": 88,
        "aa_scicode": 42,
        "aa_ifbench": null,
        "aa_critpt": 11,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.45,
        "aa_output_cost_usd_per_1m": 0.9,
        "aa_blended_cost_usd_per_1m": 0.63,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 132,
        "aa_speed_p5_tokens_per_second": 115,
        "aa_speed_p25_tokens_per_second": 122,
        "aa_speed_p75_tokens_per_second": 136,
        "aa_speed_p95_tokens_per_second": 139,
        "aa_latency_seconds": 2.23,
        "aa_latency_first_token_seconds": 17.42,
        "aa_latency_p5_seconds": 1.48,
        "aa_latency_p25_seconds": 1.76,
        "aa_latency_p75_seconds": 2.49,
        "aa_latency_p95_seconds": 4.94,
        "aa_total_response_time_seconds": 21.22,
        "aa_reasoning_time_seconds": 15.19,
        "llmdex_adjusted_performance": 39,
        "llmdex_cost_index": 99.37,
        "llmdex_speed_index": 52.05,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 59.72,
        "llmdex_efficiency_score": 72.78,
        "llmdex_performance_rank": 49,
        "llmdex_value_rank": 15,
        "llmdex_efficiency_rank": 15,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "sarvam/sarvam-105b:high",
        "family_id": "sarvam/sarvam-105b",
        "variant_id": "sarvam/sarvam-105b:high",
        "canonical_name": "Sarvam 105B (high)",
        "source_name": "Sarvam 105B (high)",
        "provider": "Sarvam",
        "creator": "Sarvam",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "sarvam-105b-high",
        "source_model_url": "https://artificialanalysis.ai/models/sarvam-105b",
        "source_rank": 166,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 26,
        "aa_omniscience_index": -60,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 47,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 10,
        "aa_gpqa": 74,
        "aa_scicode": 26,
        "aa_ifbench": 34,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.04,
        "aa_output_cost_usd_per_1m": 0.17,
        "aa_blended_cost_usd_per_1m": 0.092,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": 99.91,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 44.97,
        "llmdex_efficiency_score": 86.11,
        "llmdex_performance_rank": 166,
        "llmdex_value_rank": 138,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "sarvam/sarvam-30b:high",
        "family_id": "sarvam/sarvam-30b",
        "variant_id": "sarvam/sarvam-30b:high",
        "canonical_name": "Sarvam 30B (high)",
        "source_name": "Sarvam 30B (high)",
        "provider": "Sarvam",
        "creator": "Sarvam",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "sarvam-30b-high",
        "source_model_url": "https://artificialanalysis.ai/models/sarvam-30b",
        "source_rank": 208,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 7,
        "aa_official_coding_index": 19,
        "aa_omniscience_index": -72,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 35,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 3,
        "aa_hle": 7,
        "aa_gpqa": 63,
        "aa_scicode": 19,
        "aa_ifbench": 26,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.03,
        "aa_output_cost_usd_per_1m": 0.11,
        "aa_blended_cost_usd_per_1m": 0.062,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 7,
        "llmdex_cost_index": 99.94,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 41.85,
        "llmdex_efficiency_score": 82.22,
        "llmdex_performance_rank": 208,
        "llmdex_value_rank": 163,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "servicenow/apriel-v1-6-15b-thinker:default",
        "family_id": "servicenow/apriel-v1-6-15b-thinker",
        "variant_id": "servicenow/apriel-v1-6-15b-thinker:default",
        "canonical_name": "Apriel-v1.6-15B-Thinker",
        "source_name": "Apriel-v1.6-15B-Thinker",
        "provider": "ServiceNow",
        "creator": "ServiceNow",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "apriel-v1-6-15b-thinker",
        "source_model_url": "https://artificialanalysis.ai/models/apriel-v1-6-15b-thinker",
        "source_rank": 114,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 21,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 14,
        "aa_terminalbench_v21": null,
        "aa_tau2": 69,
        "aa_tau3_banking": null,
        "aa_lcr": 50,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 10,
        "aa_gpqa": 73,
        "aa_scicode": 37,
        "aa_ifbench": 69,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0,
        "aa_output_cost_usd_per_1m": 0,
        "aa_blended_cost_usd_per_1m": 0,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 21,
        "llmdex_cost_index": 100,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 50.62,
        "llmdex_efficiency_score": 96.67,
        "llmdex_performance_rank": 114,
        "llmdex_value_rank": 102,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "spacexai/grok-4-3:low",
        "family_id": "spacexai/grok-4-3",
        "variant_id": "spacexai/grok-4-3:low",
        "canonical_name": "Grok 4.3 (low)",
        "source_name": "Grok 4.3 (low)",
        "provider": "SpaceXAI",
        "creator": "SpaceXAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "grok-4-3-low",
        "source_model_url": "https://artificialanalysis.ai/models/grok-4-3-low",
        "source_rank": 58,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 35,
        "aa_official_coding_index": 42,
        "aa_omniscience_index": 14,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 27,
        "aa_terminalbench_v21": null,
        "aa_tau2": 89,
        "aa_tau3_banking": null,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 26,
        "aa_non_hallucination_rate": 84,
        "aa_hle": 17,
        "aa_gpqa": 84,
        "aa_scicode": 42,
        "aa_ifbench": 81,
        "aa_critpt": 1,
        "aa_mmmu_pro": 73,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 100,
        "aa_speed_p5_tokens_per_second": 75,
        "aa_speed_p25_tokens_per_second": 83,
        "aa_speed_p75_tokens_per_second": 125,
        "aa_speed_p95_tokens_per_second": 184,
        "aa_latency_seconds": 6.38,
        "aa_latency_first_token_seconds": 6.38,
        "aa_latency_p5_seconds": 3.67,
        "aa_latency_p25_seconds": 4.36,
        "aa_latency_p75_seconds": 9.22,
        "aa_latency_p95_seconds": 12.57,
        "aa_total_response_time_seconds": 11.37,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 35,
        "llmdex_cost_index": 98.25,
        "llmdex_speed_index": 28.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.59,
        "llmdex_efficiency_score": 50,
        "llmdex_performance_rank": 58,
        "llmdex_value_rank": 85,
        "llmdex_efficiency_rank": 34,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "spacexai/grok-4-3:medium",
        "family_id": "spacexai/grok-4-3",
        "variant_id": "spacexai/grok-4-3:medium",
        "canonical_name": "Grok 4.3 (medium)",
        "source_name": "Grok 4.3 (medium)",
        "provider": "SpaceXAI",
        "creator": "SpaceXAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "grok-4-3-medium",
        "source_model_url": "https://artificialanalysis.ai/models/grok-4-3-medium",
        "source_rank": 57,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 36,
        "aa_official_coding_index": 45,
        "aa_omniscience_index": 17,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 30,
        "aa_terminalbench_v21": null,
        "aa_tau2": 91,
        "aa_tau3_banking": null,
        "aa_lcr": 65,
        "aa_omniscience_accuracy": 28,
        "aa_non_hallucination_rate": 84,
        "aa_hle": 28,
        "aa_gpqa": 89,
        "aa_scicode": 45,
        "aa_ifbench": 83,
        "aa_critpt": 5,
        "aa_mmmu_pro": 76,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 106,
        "aa_speed_p5_tokens_per_second": 65,
        "aa_speed_p25_tokens_per_second": 85,
        "aa_speed_p75_tokens_per_second": 129,
        "aa_speed_p95_tokens_per_second": 178,
        "aa_latency_seconds": 15.66,
        "aa_latency_first_token_seconds": 15.66,
        "aa_latency_p5_seconds": 8.01,
        "aa_latency_p25_seconds": 10.57,
        "aa_latency_p75_seconds": 24.06,
        "aa_latency_p95_seconds": 41.87,
        "aa_total_response_time_seconds": 20.4,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 36,
        "llmdex_cost_index": 98.25,
        "llmdex_speed_index": 10.6,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 49.59,
        "llmdex_efficiency_score": 51.11,
        "llmdex_performance_rank": 57,
        "llmdex_value_rank": 109,
        "llmdex_efficiency_rank": 32,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "spacexai/grok-4-3:non-reasoning",
        "family_id": "spacexai/grok-4-3",
        "variant_id": "spacexai/grok-4-3:non-reasoning",
        "canonical_name": "Grok 4.3 (Non-reasoning)",
        "source_name": "Grok 4.3 (Non-reasoning)",
        "provider": "SpaceXAI",
        "creator": "SpaceXAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "grok-4-3-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/grok-4-3-non-reasoning",
        "source_rank": 98,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 25,
        "aa_official_coding_index": 35.5,
        "aa_omniscience_index": -32,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 30,
        "aa_terminalbench_hard": 19,
        "aa_terminalbench_v21": 34,
        "aa_tau2": 66,
        "aa_tau3_banking": 8,
        "aa_lcr": 25,
        "aa_omniscience_accuracy": 24,
        "aa_non_hallucination_rate": 26,
        "aa_hle": 6,
        "aa_gpqa": 66,
        "aa_scicode": 37,
        "aa_ifbench": 48,
        "aa_critpt": 0,
        "aa_mmmu_pro": 65,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.25,
        "aa_output_cost_usd_per_1m": 2.5,
        "aa_blended_cost_usd_per_1m": 1.75,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 100,
        "aa_speed_p5_tokens_per_second": 75,
        "aa_speed_p25_tokens_per_second": 80,
        "aa_speed_p75_tokens_per_second": 120,
        "aa_speed_p95_tokens_per_second": 141,
        "aa_latency_seconds": 1.3,
        "aa_latency_first_token_seconds": 1.3,
        "aa_latency_p5_seconds": 0.6,
        "aa_latency_p25_seconds": 0.87,
        "aa_latency_p75_seconds": 2.58,
        "aa_latency_p95_seconds": 7.06,
        "aa_total_response_time_seconds": 6.31,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 25,
        "llmdex_cost_index": 98.25,
        "llmdex_speed_index": 53.5,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.67,
        "llmdex_efficiency_score": 37.78,
        "llmdex_performance_rank": 98,
        "llmdex_value_rank": 84,
        "llmdex_efficiency_rank": 47,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "spacexai/grok-4-5:high",
        "family_id": "spacexai/grok-4-5",
        "variant_id": "spacexai/grok-4-5:high",
        "canonical_name": "Grok 4.5 (high)",
        "source_name": "Grok 4.5 (high)",
        "provider": "SpaceXAI",
        "creator": "SpaceXAI",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "grok-4-5-high",
        "source_model_url": "https://artificialanalysis.ai/models/grok-4-5",
        "source_rank": 12,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 54,
        "aa_official_coding_index": 68,
        "aa_omniscience_index": 26,
        "aa_context_window_tokens": 500000,
        "aa_gdpval": 51,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 82,
        "aa_tau2": null,
        "aa_tau3_banking": 33,
        "aa_lcr": 68,
        "aa_omniscience_accuracy": 52,
        "aa_non_hallucination_rate": 46,
        "aa_hle": 40,
        "aa_gpqa": 93,
        "aa_scicode": 54,
        "aa_ifbench": null,
        "aa_critpt": 15,
        "aa_mmmu_pro": 80,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 2,
        "aa_output_cost_usd_per_1m": 6,
        "aa_blended_cost_usd_per_1m": 3.6,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 61,
        "aa_speed_p5_tokens_per_second": 39,
        "aa_speed_p25_tokens_per_second": 47,
        "aa_speed_p75_tokens_per_second": 72,
        "aa_speed_p95_tokens_per_second": 98,
        "aa_latency_seconds": 10.26,
        "aa_latency_first_token_seconds": 10.26,
        "aa_latency_p5_seconds": 4.35,
        "aa_latency_p25_seconds": 7.05,
        "aa_latency_p75_seconds": 17.11,
        "aa_latency_p95_seconds": 27.11,
        "aa_total_response_time_seconds": 18.45,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 54,
        "llmdex_cost_index": 96.4,
        "llmdex_speed_index": 6.1,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.14,
        "llmdex_efficiency_score": 40,
        "llmdex_performance_rank": 12,
        "llmdex_value_rank": 39,
        "llmdex_efficiency_rank": 45,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "stepfun/step-3-5-flash-2603:default",
        "family_id": "stepfun/step-3-5-flash-2603",
        "variant_id": "stepfun/step-3-5-flash-2603:default",
        "canonical_name": "Step 3.5 Flash 2603",
        "source_name": "Step 3.5 Flash 2603",
        "provider": "StepFun",
        "creator": "StepFun",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "step-3-5-flash-2603",
        "source_model_url": "https://artificialanalysis.ai/models/step-3-5-flash",
        "source_rank": 92,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -44,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 33,
        "aa_terminalbench_v21": null,
        "aa_tau2": 87,
        "aa_tau3_banking": null,
        "aa_lcr": 54,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 8,
        "aa_hle": 23,
        "aa_gpqa": 83,
        "aa_scicode": 39,
        "aa_ifbench": 67,
        "aa_critpt": 2,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.3,
        "aa_blended_cost_usd_per_1m": 0.18,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 291,
        "aa_speed_p5_tokens_per_second": 219,
        "aa_speed_p25_tokens_per_second": 264,
        "aa_speed_p75_tokens_per_second": 314,
        "aa_speed_p95_tokens_per_second": 359,
        "aa_latency_seconds": 1.17,
        "aa_latency_first_token_seconds": 8.04,
        "aa_latency_p5_seconds": 0.94,
        "aa_latency_p25_seconds": 1.03,
        "aa_latency_p75_seconds": 1.28,
        "aa_latency_p95_seconds": 1.9,
        "aa_total_response_time_seconds": 9.75,
        "aa_reasoning_time_seconds": 6.87,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": 99.82,
        "llmdex_speed_index": 73.25,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.6,
        "llmdex_efficiency_score": 86.67,
        "llmdex_performance_rank": 92,
        "llmdex_value_rank": 32,
        "llmdex_efficiency_rank": 8,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "stepfun/step-3-7-flash:default",
        "family_id": "stepfun/step-3-7-flash",
        "variant_id": "stepfun/step-3-7-flash:default",
        "canonical_name": "Step 3.7 Flash",
        "source_name": "Step 3.7 Flash",
        "provider": "StepFun",
        "creator": "StepFun",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "step-3-7-flash",
        "source_model_url": "https://artificialanalysis.ai/models/step-3-7-flash",
        "source_rank": 79,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 30,
        "aa_official_coding_index": 39.5,
        "aa_omniscience_index": -38,
        "aa_context_window_tokens": 262000,
        "aa_gdpval": 26,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": 39,
        "aa_tau2": 99,
        "aa_tau3_banking": 11,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 16,
        "aa_hle": 20,
        "aa_gpqa": 81,
        "aa_scicode": 40,
        "aa_ifbench": 67,
        "aa_critpt": 2,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": 15,
        "aa_itbench": 30,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.2,
        "aa_output_cost_usd_per_1m": 1.15,
        "aa_blended_cost_usd_per_1m": 0.58,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 381,
        "aa_speed_p5_tokens_per_second": 342,
        "aa_speed_p25_tokens_per_second": 358,
        "aa_speed_p75_tokens_per_second": 424,
        "aa_speed_p95_tokens_per_second": 450,
        "aa_latency_seconds": 0.88,
        "aa_latency_first_token_seconds": 6.13,
        "aa_latency_p5_seconds": 0.72,
        "aa_latency_p25_seconds": 0.77,
        "aa_latency_p75_seconds": 0.97,
        "aa_latency_p95_seconds": 1.23,
        "aa_total_response_time_seconds": 7.44,
        "aa_reasoning_time_seconds": 5.25,
        "llmdex_adjusted_performance": 30,
        "llmdex_cost_index": 99.42,
        "llmdex_speed_index": 83.7,
        "llmdex_coverage_score": 93.8,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 61.57,
        "llmdex_efficiency_score": 69.44,
        "llmdex_performance_rank": 79,
        "llmdex_value_rank": 5,
        "llmdex_efficiency_rank": 17,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "stepfun/step3-vl-10b:default",
        "family_id": "stepfun/step3-vl-10b",
        "variant_id": "stepfun/step3-vl-10b:default",
        "canonical_name": "Step3 VL 10B",
        "source_name": "Step3 VL 10B",
        "provider": "StepFun",
        "creator": "StepFun",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "step3-vl-10b",
        "source_model_url": "https://artificialanalysis.ai/models/step-3-vl-10b",
        "source_rank": 180,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 31,
        "aa_omniscience_index": -59,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 16,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 18,
        "aa_hle": 10,
        "aa_gpqa": 69,
        "aa_scicode": 31,
        "aa_ifbench": 50,
        "aa_critpt": 0,
        "aa_mmmu_pro": 64,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 180,
        "llmdex_value_rank": 223,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "swiss-ai-initiative/apertus-70b-instruct:default",
        "family_id": "swiss-ai-initiative/apertus-70b-instruct",
        "variant_id": "swiss-ai-initiative/apertus-70b-instruct:default",
        "canonical_name": "Apertus 70B Instruct",
        "source_name": "Apertus 70B Instruct",
        "provider": "Swiss AI Initiative",
        "creator": "Swiss AI Initiative",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "apertus-70b-instruct",
        "source_model_url": "https://artificialanalysis.ai/models/apertus-70b-instruct",
        "source_rank": 245,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 2,
        "aa_official_coding_index": 6,
        "aa_omniscience_index": -55,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 13,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 13,
        "aa_non_hallucination_rate": 21,
        "aa_hle": 5,
        "aa_gpqa": 27,
        "aa_scicode": 6,
        "aa_ifbench": 26,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.82,
        "aa_output_cost_usd_per_1m": 2.92,
        "aa_blended_cost_usd_per_1m": 1.66,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 2,
        "llmdex_cost_index": 98.34,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 38.13,
        "llmdex_efficiency_score": 1.11,
        "llmdex_performance_rank": 245,
        "llmdex_value_rank": 178,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "swiss-ai-initiative/apertus-8b-instruct:default",
        "family_id": "swiss-ai-initiative/apertus-8b-instruct",
        "variant_id": "swiss-ai-initiative/apertus-8b-instruct:default",
        "canonical_name": "Apertus 8B Instruct",
        "source_name": "Apertus 8B Instruct",
        "provider": "Swiss AI Initiative",
        "creator": "Swiss AI Initiative",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "apertus-8b-instruct",
        "source_model_url": "https://artificialanalysis.ai/models/apertus-8b-instruct",
        "source_rank": 254,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 1,
        "aa_official_coding_index": 4,
        "aa_omniscience_index": -75,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 0,
        "aa_terminalbench_v21": null,
        "aa_tau2": 11,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 10,
        "aa_non_hallucination_rate": 5,
        "aa_hle": 5,
        "aa_gpqa": 26,
        "aa_scicode": 4,
        "aa_ifbench": 22,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.1,
        "aa_output_cost_usd_per_1m": 0.2,
        "aa_blended_cost_usd_per_1m": 0.14,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 1,
        "llmdex_cost_index": 99.86,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 50,
        "llmdex_confidence_factor": 0.75,
        "llmdex_composite_index": 38.07,
        "llmdex_efficiency_score": 21.67,
        "llmdex_performance_rank": 254,
        "llmdex_value_rank": 180,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "tencent/hy3-preview:non-reasoning-preview",
        "family_id": "tencent/hy3-preview",
        "variant_id": "tencent/hy3-preview:non-reasoning-preview",
        "canonical_name": "Hy3-preview (non-reasoning)",
        "source_name": "Hy3-preview (non-reasoning)",
        "provider": "Tencent",
        "creator": "Tencent",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "hy3-preview-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/hy3-non-reasoning",
        "source_rank": 90,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 26,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -36,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 32,
        "aa_terminalbench_v21": null,
        "aa_tau2": 68,
        "aa_tau3_banking": null,
        "aa_lcr": 34,
        "aa_omniscience_accuracy": 22,
        "aa_non_hallucination_rate": 24,
        "aa_hle": 6,
        "aa_gpqa": 73,
        "aa_scicode": 39,
        "aa_ifbench": 48,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.06,
        "aa_output_cost_usd_per_1m": 0.23,
        "aa_blended_cost_usd_per_1m": 0.128,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 127,
        "aa_speed_p5_tokens_per_second": 77,
        "aa_speed_p25_tokens_per_second": 105,
        "aa_speed_p75_tokens_per_second": 152,
        "aa_speed_p95_tokens_per_second": 197,
        "aa_latency_seconds": 3.65,
        "aa_latency_first_token_seconds": 3.65,
        "aa_latency_p5_seconds": 2.22,
        "aa_latency_p25_seconds": 3.28,
        "aa_latency_p75_seconds": 4.01,
        "aa_latency_p95_seconds": 4.21,
        "aa_total_response_time_seconds": 7.58,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 26,
        "llmdex_cost_index": 99.87,
        "llmdex_speed_index": 44.45,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 51.85,
        "llmdex_efficiency_score": 89.44,
        "llmdex_performance_rank": 90,
        "llmdex_value_rank": 94,
        "llmdex_efficiency_rank": 4,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "tencent/hy3-preview:preview",
        "family_id": "tencent/hy3-preview",
        "variant_id": "tencent/hy3-preview:preview",
        "canonical_name": "Hy3-preview",
        "source_name": "Hy3-preview",
        "provider": "Tencent",
        "creator": "Tencent",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hy3-preview",
        "source_model_url": "https://artificialanalysis.ai/models/hy3-preview",
        "source_rank": 67,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 41,
        "aa_omniscience_index": -35,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 34,
        "aa_terminalbench_v21": null,
        "aa_tau2": 93,
        "aa_tau3_banking": null,
        "aa_lcr": 55,
        "aa_omniscience_accuracy": 28,
        "aa_non_hallucination_rate": 13,
        "aa_hle": 26,
        "aa_gpqa": 87,
        "aa_scicode": 41,
        "aa_ifbench": 63,
        "aa_critpt": 5,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.06,
        "aa_output_cost_usd_per_1m": 0.23,
        "aa_blended_cost_usd_per_1m": 0.128,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 131,
        "aa_speed_p5_tokens_per_second": 95,
        "aa_speed_p25_tokens_per_second": 112,
        "aa_speed_p75_tokens_per_second": 157,
        "aa_speed_p95_tokens_per_second": 195,
        "aa_latency_seconds": 3.22,
        "aa_latency_first_token_seconds": 18.47,
        "aa_latency_p5_seconds": 2.47,
        "aa_latency_p25_seconds": 2.72,
        "aa_latency_p75_seconds": 3.65,
        "aa_latency_p95_seconds": 5.2,
        "aa_total_response_time_seconds": 22.28,
        "aa_reasoning_time_seconds": 15.25,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 99.87,
        "llmdex_speed_index": 47,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.36,
        "llmdex_efficiency_score": 92.78,
        "llmdex_performance_rank": 67,
        "llmdex_value_rank": 48,
        "llmdex_efficiency_rank": 2,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "tencent/hy3:default",
        "family_id": "tencent/hy3",
        "variant_id": "tencent/hy3:default",
        "canonical_name": "Hy3",
        "source_name": "Hy3",
        "provider": "Tencent",
        "creator": "Tencent",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "hy3",
        "source_model_url": "https://artificialanalysis.ai/models/hy3",
        "source_rank": 40,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 41,
        "aa_official_coding_index": 56,
        "aa_omniscience_index": -19,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 36,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 64,
        "aa_tau2": null,
        "aa_tau3_banking": 21,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 32,
        "aa_non_hallucination_rate": 27,
        "aa_hle": 32,
        "aa_gpqa": 90,
        "aa_scicode": 48,
        "aa_ifbench": null,
        "aa_critpt": 5,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.58,
        "aa_blended_cost_usd_per_1m": 0.316,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 62,
        "aa_speed_p5_tokens_per_second": 31,
        "aa_speed_p25_tokens_per_second": 44,
        "aa_speed_p75_tokens_per_second": 72,
        "aa_speed_p95_tokens_per_second": 110,
        "aa_latency_seconds": 2.7,
        "aa_latency_first_token_seconds": 35.15,
        "aa_latency_p5_seconds": 0.57,
        "aa_latency_p25_seconds": 0.78,
        "aa_latency_p75_seconds": 3.14,
        "aa_latency_p95_seconds": 3.89,
        "aa_total_response_time_seconds": 43.27,
        "aa_reasoning_time_seconds": 32.46,
        "llmdex_adjusted_performance": 41,
        "llmdex_cost_index": 99.68,
        "llmdex_speed_index": 42.7,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 58.94,
        "llmdex_efficiency_score": 85.56,
        "llmdex_performance_rank": 40,
        "llmdex_value_rank": 19,
        "llmdex_efficiency_rank": 9,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "thinking-machines/inkling:default",
        "family_id": "thinking-machines/inkling",
        "variant_id": "thinking-machines/inkling:default",
        "canonical_name": "Inkling",
        "source_name": "Inkling",
        "provider": "Thinking Machines",
        "creator": "Thinking Machines",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "inkling",
        "source_model_url": "https://artificialanalysis.ai/models/inkling",
        "source_rank": 43,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 41,
        "aa_official_coding_index": 50.5,
        "aa_omniscience_index": 2,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 37,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 55,
        "aa_tau2": null,
        "aa_tau3_banking": 24,
        "aa_lcr": 63,
        "aa_omniscience_accuracy": 40,
        "aa_non_hallucination_rate": 37,
        "aa_hle": 30,
        "aa_gpqa": 87,
        "aa_scicode": 46,
        "aa_ifbench": null,
        "aa_critpt": 5,
        "aa_mmmu_pro": 73,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.87,
        "aa_output_cost_usd_per_1m": 4.68,
        "aa_blended_cost_usd_per_1m": 2.994,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 82,
        "aa_speed_p5_tokens_per_second": 40,
        "aa_speed_p25_tokens_per_second": 60,
        "aa_speed_p75_tokens_per_second": 89,
        "aa_speed_p95_tokens_per_second": 97,
        "aa_latency_seconds": 1.79,
        "aa_latency_first_token_seconds": 26.21,
        "aa_latency_p5_seconds": 1.64,
        "aa_latency_p25_seconds": 1.69,
        "aa_latency_p75_seconds": 2.47,
        "aa_latency_p95_seconds": 4.44,
        "aa_total_response_time_seconds": 32.32,
        "aa_reasoning_time_seconds": 24.42,
        "llmdex_adjusted_performance": 41,
        "llmdex_cost_index": 97.01,
        "llmdex_speed_index": 49.25,
        "llmdex_coverage_score": 78.1,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 59.45,
        "llmdex_efficiency_score": 36.11,
        "llmdex_performance_rank": 43,
        "llmdex_value_rank": 16,
        "llmdex_efficiency_rank": 48,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "tii-uae/falcon-h1r-7b:default",
        "family_id": "tii-uae/falcon-h1r-7b",
        "variant_id": "tii-uae/falcon-h1r-7b:default",
        "canonical_name": "Falcon-H1R-7B",
        "source_name": "Falcon-H1R-7B",
        "provider": "TII UAE",
        "creator": "TII UAE",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "falcon-h1r-7b",
        "source_model_url": "https://artificialanalysis.ai/models/falcon-h1r-7b",
        "source_rank": 177,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 10,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 28,
        "aa_tau3_banking": null,
        "aa_lcr": 9,
        "aa_omniscience_accuracy": 14,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 11,
        "aa_gpqa": 66,
        "aa_scicode": 25,
        "aa_ifbench": 54,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 10,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 10,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 177,
        "llmdex_value_rank": 216,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "trillion-labs/tri-21b-think-preview:preview",
        "family_id": "trillion-labs/tri-21b-think-preview",
        "variant_id": "trillion-labs/tri-21b-think-preview:preview",
        "canonical_name": "Tri-21B-think Preview",
        "source_name": "Tri-21B-think Preview",
        "provider": "Trillion Labs",
        "creator": "Trillion Labs",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "tri-21b-think-preview",
        "source_model_url": "https://artificialanalysis.ai/models/tri-21b-think-preview",
        "source_rank": 156,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 18,
        "aa_omniscience_index": -55,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 93,
        "aa_tau3_banking": null,
        "aa_lcr": 15,
        "aa_omniscience_accuracy": 9,
        "aa_non_hallucination_rate": 30,
        "aa_hle": 6,
        "aa_gpqa": 54,
        "aa_scicode": 18,
        "aa_ifbench": 47,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 14,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 156,
        "llmdex_value_rank": 207,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "trillion-labs/tri-21b-think:default",
        "family_id": "trillion-labs/tri-21b-think",
        "variant_id": "trillion-labs/tri-21b-think:default",
        "canonical_name": "Tri-21B-Think",
        "source_name": "Tri-21B-Think",
        "provider": "Trillion Labs",
        "creator": "Trillion Labs",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "tri-21b-think",
        "source_model_url": "https://artificialanalysis.ai/models/tri-21b-think-v0-5",
        "source_rank": 164,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 12,
        "aa_official_coding_index": 17,
        "aa_omniscience_index": -63,
        "aa_context_window_tokens": 32000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 1,
        "aa_terminalbench_v21": null,
        "aa_tau2": 81,
        "aa_tau3_banking": null,
        "aa_lcr": 11,
        "aa_omniscience_accuracy": 12,
        "aa_non_hallucination_rate": 15,
        "aa_hle": 6,
        "aa_gpqa": 60,
        "aa_scicode": 17,
        "aa_ifbench": 55,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 12,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 12,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 164,
        "llmdex_value_rank": 213,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "upstage/solar-open-100b:reasoning",
        "family_id": "upstage/solar-open-100b",
        "variant_id": "upstage/solar-open-100b:reasoning",
        "canonical_name": "Solar Open 100B (reasoning)",
        "source_name": "Solar Open 100B (reasoning)",
        "provider": "Upstage",
        "creator": "Upstage",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "solar-open-100b-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/solar-open-100b-reasoning",
        "source_rank": 144,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 15,
        "aa_official_coding_index": 27,
        "aa_omniscience_index": -54,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 2,
        "aa_terminalbench_v21": null,
        "aa_tau2": 48,
        "aa_tau3_banking": null,
        "aa_lcr": 36,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 9,
        "aa_gpqa": 66,
        "aa_scicode": 27,
        "aa_ifbench": 58,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 15,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 15,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 144,
        "llmdex_value_rank": 204,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "upstage/solar-pro-2:default",
        "family_id": "upstage/solar-pro-2",
        "variant_id": "upstage/solar-pro-2:default",
        "canonical_name": "Solar Pro 2",
        "source_name": "Solar Pro 2",
        "provider": "Upstage",
        "creator": "Upstage",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": false,
        "source_model_id": "solar-pro-2",
        "source_model_url": "https://artificialanalysis.ai/models/solar-pro-2",
        "source_rank": 200,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 8,
        "aa_official_coding_index": 25,
        "aa_omniscience_index": -62,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 5,
        "aa_terminalbench_v21": null,
        "aa_tau2": 32,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 16,
        "aa_non_hallucination_rate": 9,
        "aa_hle": 4,
        "aa_gpqa": 56,
        "aa_scicode": 25,
        "aa_ifbench": 34,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 8,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 8,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 200,
        "llmdex_value_rank": 224,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "upstage/solar-pro-2:reasoning",
        "family_id": "upstage/solar-pro-2",
        "variant_id": "upstage/solar-pro-2:reasoning",
        "canonical_name": "Solar Pro 2 (reasoning)",
        "source_name": "Solar Pro 2 (reasoning)",
        "provider": "Upstage",
        "creator": "Upstage",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "solar-pro-2-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/solar-pro-2-reasoning",
        "source_rank": 185,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 9,
        "aa_official_coding_index": 30,
        "aa_omniscience_index": -57,
        "aa_context_window_tokens": 65500,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 3,
        "aa_terminalbench_v21": null,
        "aa_tau2": 28,
        "aa_tau3_banking": null,
        "aa_lcr": 0,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 6,
        "aa_hle": 7,
        "aa_gpqa": 69,
        "aa_scicode": 30,
        "aa_ifbench": 37,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 9,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 9,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 185,
        "llmdex_value_rank": 222,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "upstage/solar-pro-3:default",
        "family_id": "upstage/solar-pro-3",
        "variant_id": "upstage/solar-pro-3:default",
        "canonical_name": "Solar Pro 3",
        "source_name": "Solar Pro 3",
        "provider": "Upstage",
        "creator": "Upstage",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "solar-pro-3",
        "source_model_url": "https://artificialanalysis.ai/models/solar-pro-3",
        "source_rank": 153,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 14,
        "aa_official_coding_index": 18.5,
        "aa_omniscience_index": -54,
        "aa_context_window_tokens": 128000,
        "aa_gdpval": 0,
        "aa_terminalbench_hard": 8,
        "aa_terminalbench_v21": 12,
        "aa_tau2": 86,
        "aa_tau3_banking": 8,
        "aa_lcr": 27,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 12,
        "aa_hle": 10,
        "aa_gpqa": 72,
        "aa_scicode": 25,
        "aa_ifbench": 71,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 14,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 14,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 153,
        "llmdex_value_rank": 206,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-5-pro:default",
        "family_id": "xiaomi/mimo-v2-5-pro",
        "variant_id": "xiaomi/mimo-v2-5-pro:default",
        "canonical_name": "MiMo-V2.5-Pro",
        "source_name": "MiMo-V2.5-Pro",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-5-pro",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-5-pro",
        "source_rank": 37,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 42,
        "aa_official_coding_index": 57.5,
        "aa_omniscience_index": 4,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 38,
        "aa_terminalbench_hard": 43,
        "aa_terminalbench_v21": 65,
        "aa_tau2": 94,
        "aa_tau3_banking": 9,
        "aa_lcr": 73,
        "aa_omniscience_accuracy": 23,
        "aa_non_hallucination_rate": 75,
        "aa_hle": 34,
        "aa_gpqa": 87,
        "aa_scicode": 50,
        "aa_ifbench": 80,
        "aa_critpt": 4,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 2,
        "aa_itbench": 38,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.43,
        "aa_output_cost_usd_per_1m": 0.87,
        "aa_blended_cost_usd_per_1m": 0.606,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 69,
        "aa_speed_p5_tokens_per_second": 53,
        "aa_speed_p25_tokens_per_second": 58,
        "aa_speed_p75_tokens_per_second": 75,
        "aa_speed_p95_tokens_per_second": 79,
        "aa_latency_seconds": 2.88,
        "aa_latency_first_token_seconds": 31.98,
        "aa_latency_p5_seconds": 2.12,
        "aa_latency_p25_seconds": 2.32,
        "aa_latency_p75_seconds": 3.96,
        "aa_latency_p95_seconds": 4.38,
        "aa_total_response_time_seconds": 39.26,
        "aa_reasoning_time_seconds": 29.11,
        "llmdex_adjusted_performance": 42,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": 42.5,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 59.32,
        "llmdex_efficiency_score": 75.56,
        "llmdex_performance_rank": 37,
        "llmdex_value_rank": 17,
        "llmdex_efficiency_rank": 13,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-5-pro:non-reasoning",
        "family_id": "xiaomi/mimo-v2-5-pro",
        "variant_id": "xiaomi/mimo-v2-5-pro:non-reasoning",
        "canonical_name": "MiMo-V2.5-Pro (non-reasoning)",
        "source_name": "MiMo-V2.5-Pro (non-reasoning)",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "mimo-v2-5-pro-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-5-pro-non-reasoning",
        "source_rank": 87,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 28,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -38,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": null,
        "aa_tau2": 73,
        "aa_tau3_banking": null,
        "aa_lcr": 35,
        "aa_omniscience_accuracy": 27,
        "aa_non_hallucination_rate": 11,
        "aa_hle": 13,
        "aa_gpqa": 76,
        "aa_scicode": 39,
        "aa_ifbench": 43,
        "aa_critpt": 1,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.43,
        "aa_output_cost_usd_per_1m": 0.87,
        "aa_blended_cost_usd_per_1m": 0.606,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 66,
        "aa_speed_p5_tokens_per_second": 52,
        "aa_speed_p25_tokens_per_second": 58,
        "aa_speed_p75_tokens_per_second": 70,
        "aa_speed_p95_tokens_per_second": 78,
        "aa_latency_seconds": 3.04,
        "aa_latency_first_token_seconds": 3.04,
        "aa_latency_p5_seconds": 2.35,
        "aa_latency_p25_seconds": 2.64,
        "aa_latency_p75_seconds": 3.58,
        "aa_latency_p95_seconds": 6.27,
        "aa_total_response_time_seconds": 10.57,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 28,
        "llmdex_cost_index": 99.39,
        "llmdex_speed_index": 41.4,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 52.1,
        "llmdex_efficiency_score": 66.67,
        "llmdex_performance_rank": 87,
        "llmdex_value_rank": 90,
        "llmdex_efficiency_rank": 20,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-5:default",
        "family_id": "xiaomi/mimo-v2-5",
        "variant_id": "xiaomi/mimo-v2-5:default",
        "canonical_name": "MiMo-V2.5",
        "source_name": "MiMo-V2.5",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-5",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-5-0424",
        "source_rank": 53,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 37,
        "aa_official_coding_index": 53.5,
        "aa_omniscience_index": -9,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 32,
        "aa_terminalbench_hard": 42,
        "aa_terminalbench_v21": 64,
        "aa_tau2": 91,
        "aa_tau3_banking": 7,
        "aa_lcr": 63,
        "aa_omniscience_accuracy": 17,
        "aa_non_hallucination_rate": 68,
        "aa_hle": 25,
        "aa_gpqa": 85,
        "aa_scicode": 43,
        "aa_ifbench": 67,
        "aa_critpt": 4,
        "aa_mmmu_pro": 75,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 0.14,
        "aa_output_cost_usd_per_1m": 0.28,
        "aa_blended_cost_usd_per_1m": 0.196,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 65,
        "aa_speed_p5_tokens_per_second": 50,
        "aa_speed_p25_tokens_per_second": 58,
        "aa_speed_p75_tokens_per_second": 70,
        "aa_speed_p95_tokens_per_second": 82,
        "aa_latency_seconds": 3.57,
        "aa_latency_first_token_seconds": 34.33,
        "aa_latency_p5_seconds": 2.26,
        "aa_latency_p25_seconds": 2.91,
        "aa_latency_p75_seconds": 4.97,
        "aa_latency_p95_seconds": 8.11,
        "aa_total_response_time_seconds": 42.02,
        "aa_reasoning_time_seconds": 30.76,
        "llmdex_adjusted_performance": 37,
        "llmdex_cost_index": 99.8,
        "llmdex_speed_index": 38.65,
        "llmdex_coverage_score": 87.5,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 56.17,
        "llmdex_efficiency_score": 88.61,
        "llmdex_performance_rank": 53,
        "llmdex_value_rank": 52,
        "llmdex_efficiency_rank": 6,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-flash-feb-2026:default",
        "family_id": "xiaomi/mimo-v2-flash-feb-2026",
        "variant_id": "xiaomi/mimo-v2-flash-feb-2026:default",
        "canonical_name": "MiMo-V2-Flash (Feb 2026)",
        "source_name": "MiMo-V2-Flash (Feb 2026)",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-flash-feb-2026",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-0206",
        "source_rank": 70,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 33,
        "aa_official_coding_index": 38,
        "aa_omniscience_index": -18,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 31,
        "aa_terminalbench_v21": null,
        "aa_tau2": 93,
        "aa_tau3_banking": null,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 52,
        "aa_hle": 20,
        "aa_gpqa": 84,
        "aa_scicode": 38,
        "aa_ifbench": 72,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 33,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 43.8,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 33,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 70,
        "llmdex_value_rank": 187,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-flash:default",
        "family_id": "xiaomi/mimo-v2-flash",
        "variant_id": "xiaomi/mimo-v2-flash:default",
        "canonical_name": "MiMo-V2-Flash",
        "source_name": "MiMo-V2-Flash",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-flash",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-flash",
        "source_rank": 99,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 25,
        "aa_official_coding_index": 44,
        "aa_omniscience_index": -48,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": 17,
        "aa_terminalbench_hard": 26,
        "aa_terminalbench_v21": 62,
        "aa_tau2": 84,
        "aa_tau3_banking": 3,
        "aa_lcr": 31,
        "aa_omniscience_accuracy": 15,
        "aa_non_hallucination_rate": 25,
        "aa_hle": 8,
        "aa_gpqa": 66,
        "aa_scicode": 26,
        "aa_ifbench": 40,
        "aa_critpt": 0,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 25,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 53.1,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 25,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 99,
        "llmdex_value_rank": 191,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-omni-0327:default",
        "family_id": "xiaomi/mimo-v2-omni-0327",
        "variant_id": "xiaomi/mimo-v2-omni-0327:default",
        "canonical_name": "MiMo-V2-Omni-0327",
        "source_name": "MiMo-V2-Omni-0327",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-omni-0327",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-omni-0327",
        "source_rank": 56,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 36,
        "aa_official_coding_index": 39,
        "aa_omniscience_index": -14,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 36,
        "aa_terminalbench_v21": null,
        "aa_tau2": 88,
        "aa_tau3_banking": null,
        "aa_lcr": 64,
        "aa_omniscience_accuracy": 18,
        "aa_non_hallucination_rate": 60,
        "aa_hle": 20,
        "aa_gpqa": 85,
        "aa_scicode": 39,
        "aa_ifbench": 67,
        "aa_critpt": 1,
        "aa_mmmu_pro": 74,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 36,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 36,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 56,
        "llmdex_value_rank": 184,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "xiaomi/mimo-v2-omni:default",
        "family_id": "xiaomi/mimo-v2-omni",
        "variant_id": "xiaomi/mimo-v2-omni:default",
        "canonical_name": "MiMo-V2-Omni",
        "source_name": "MiMo-V2-Omni",
        "provider": "Xiaomi",
        "creator": "Xiaomi",
        "availability_class": "proprietary",
        "license_type": "Proprietary",
        "is_open_weights": false,
        "is_family_representative": true,
        "source_model_id": "mimo-v2-omni",
        "source_model_url": "https://artificialanalysis.ai/models/mimo-v2-omni",
        "source_rank": 59,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 35,
        "aa_official_coding_index": 37,
        "aa_omniscience_index": -17,
        "aa_context_window_tokens": 256000,
        "aa_gdpval": null,
        "aa_terminalbench_hard": 35,
        "aa_terminalbench_v21": null,
        "aa_tau2": 91,
        "aa_tau3_banking": null,
        "aa_lcr": 67,
        "aa_omniscience_accuracy": 19,
        "aa_non_hallucination_rate": 56,
        "aa_hle": 20,
        "aa_gpqa": 83,
        "aa_scicode": 37,
        "aa_ifbench": 54,
        "aa_critpt": 1,
        "aa_mmmu_pro": 70,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": null,
        "aa_output_cost_usd_per_1m": null,
        "aa_blended_cost_usd_per_1m": null,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": null,
        "aa_speed_p5_tokens_per_second": null,
        "aa_speed_p25_tokens_per_second": null,
        "aa_speed_p75_tokens_per_second": null,
        "aa_speed_p95_tokens_per_second": null,
        "aa_latency_seconds": null,
        "aa_latency_first_token_seconds": null,
        "aa_latency_p5_seconds": null,
        "aa_latency_p25_seconds": null,
        "aa_latency_p75_seconds": null,
        "aa_latency_p95_seconds": null,
        "aa_total_response_time_seconds": null,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 35,
        "llmdex_cost_index": null,
        "llmdex_speed_index": null,
        "llmdex_coverage_score": 46.9,
        "llmdex_confidence_factor": 0.5,
        "llmdex_composite_index": 35,
        "llmdex_efficiency_score": null,
        "llmdex_performance_rank": 59,
        "llmdex_value_rank": 185,
        "llmdex_efficiency_rank": null,
        "llmdex_performance_component_count": 2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "z-ai/glm-5-2:max",
        "family_id": "z-ai/glm-5-2",
        "variant_id": "z-ai/glm-5-2:max",
        "canonical_name": "GLM-5.2 (max)",
        "source_name": "GLM-5.2 (max)",
        "provider": "Z AI",
        "creator": "Z AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": true,
        "source_model_id": "glm-5-2-max",
        "source_model_url": "https://artificialanalysis.ai/models/glm-5-2",
        "source_rank": 17,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 51,
        "aa_official_coding_index": 64,
        "aa_omniscience_index": 4,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 51,
        "aa_terminalbench_hard": 51,
        "aa_terminalbench_v21": 78,
        "aa_tau2": 99,
        "aa_tau3_banking": 27,
        "aa_lcr": 71,
        "aa_omniscience_accuracy": 25,
        "aa_non_hallucination_rate": 72,
        "aa_hle": 40,
        "aa_gpqa": 89,
        "aa_scicode": 50,
        "aa_ifbench": 73,
        "aa_critpt": 21,
        "aa_mmmu_pro": null,
        "aa_apex_agents": 34,
        "aa_itbench": 43,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.4,
        "aa_output_cost_usd_per_1m": 4.4,
        "aa_blended_cost_usd_per_1m": 2.6,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 191,
        "aa_speed_p5_tokens_per_second": 40,
        "aa_speed_p25_tokens_per_second": 72,
        "aa_speed_p75_tokens_per_second": 347,
        "aa_speed_p95_tokens_per_second": 601,
        "aa_latency_seconds": 1.35,
        "aa_latency_first_token_seconds": 11.81,
        "aa_latency_p5_seconds": 0.7,
        "aa_latency_p25_seconds": 0.98,
        "aa_latency_p75_seconds": 1.95,
        "aa_latency_p95_seconds": 9.5,
        "aa_total_response_time_seconds": 14.43,
        "aa_reasoning_time_seconds": 10.47,
        "llmdex_adjusted_performance": 51,
        "llmdex_cost_index": 97.4,
        "llmdex_speed_index": 62.35,
        "llmdex_coverage_score": 90.6,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 67.19,
        "llmdex_efficiency_score": 49.44,
        "llmdex_performance_rank": 17,
        "llmdex_value_rank": 1,
        "llmdex_efficiency_rank": 35,
        "llmdex_performance_component_count": 4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "Artificial Analysis",
        "model_key": "z-ai/glm-5-2:non-reasoning",
        "family_id": "z-ai/glm-5-2",
        "variant_id": "z-ai/glm-5-2:non-reasoning",
        "canonical_name": "GLM-5.2 (non-reasoning)",
        "source_name": "GLM-5.2 (non-reasoning)",
        "provider": "Z AI",
        "creator": "Z AI",
        "availability_class": "open_weights",
        "license_type": "Open",
        "is_open_weights": true,
        "is_family_representative": false,
        "source_model_id": "glm-5-2-non-reasoning",
        "source_model_url": "https://artificialanalysis.ai/models/glm-5-2-non-reasoning",
        "source_rank": 63,
        "methodology_version": "Artificial Analysis v4.1",
        "aa_intelligence_score": 34,
        "aa_official_coding_index": 44,
        "aa_omniscience_index": -6,
        "aa_context_window_tokens": 1000000,
        "aa_gdpval": 44,
        "aa_terminalbench_hard": null,
        "aa_terminalbench_v21": 52,
        "aa_tau2": null,
        "aa_tau3_banking": 16,
        "aa_lcr": 37,
        "aa_omniscience_accuracy": 20,
        "aa_non_hallucination_rate": 66,
        "aa_hle": 8,
        "aa_gpqa": 69,
        "aa_scicode": 36,
        "aa_ifbench": null,
        "aa_critpt": 3,
        "aa_mmmu_pro": null,
        "aa_apex_agents": null,
        "aa_itbench": null,
        "aa_aime25": null,
        "aa_livecodebench": null,
        "aa_arena_elo": null,
        "aa_reasoning_score": null,
        "aa_multimodal_score": null,
        "aa_cost_per_task_usd": null,
        "aa_input_cost_usd_per_1m": 1.35,
        "aa_output_cost_usd_per_1m": 4.25,
        "aa_blended_cost_usd_per_1m": 2.51,
        "aa_cache_read_cost_usd_per_1m": null,
        "aa_cache_write_cost_usd_per_1m": null,
        "aa_tokens_per_second": 126,
        "aa_speed_p5_tokens_per_second": 37,
        "aa_speed_p25_tokens_per_second": 64,
        "aa_speed_p75_tokens_per_second": 288,
        "aa_speed_p95_tokens_per_second": 456,
        "aa_latency_seconds": 1.52,
        "aa_latency_first_token_seconds": 1.52,
        "aa_latency_p5_seconds": 1.05,
        "aa_latency_p25_seconds": 1.2,
        "aa_latency_p75_seconds": 2.2,
        "aa_latency_p95_seconds": 11.12,
        "aa_total_response_time_seconds": 5.49,
        "aa_reasoning_time_seconds": null,
        "llmdex_adjusted_performance": 34,
        "llmdex_cost_index": 97.49,
        "llmdex_speed_index": 55,
        "llmdex_coverage_score": 75,
        "llmdex_confidence_factor": 1,
        "llmdex_composite_index": 57.25,
        "llmdex_efficiency_score": 35.56,
        "llmdex_performance_rank": 63,
        "llmdex_value_rank": 35,
        "llmdex_efficiency_rank": 49,
        "llmdex_performance_component_count": 4
      }
    ]
  },
  "llmstats": {
    "general": [
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-3-7-sonnet-20250219",
        "source_name": "Claude 3.7 Sonnet",
        "original_source_name": "25Claude 3.7 Sonnet",
        "canonical_name": "Claude 3.7 Sonnet",
        "family_id": "unknown/claude-3-7-sonnet",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/claude-3-7-sonnet-20250219",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 58.4,
        "benchmark_llmstats_tau_bench_retail": 81.2,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-fable-5",
        "source_name": "Claude Fable 5",
        "original_source_name": null,
        "canonical_name": "Claude Fable 5",
        "family_id": "anthropic/claude-fable-5",
        "provider": "Anthropic",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": null,
        "category_score": null,
        "match_status": "matched_manual",
        "source_model_url": "https://llm-stats.com/models/claude-fable-5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 70,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 53.5,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 90,
        "benchmark_llmstats_gdpval_aa": 60.5,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 64.5,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 80,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 84.3,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 95
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-haiku-4-5-20251001",
        "source_name": "Claude Haiku 4.5",
        "original_source_name": "17Claude Haiku 4.5",
        "canonical_name": "Claude Haiku 4.5",
        "family_id": "unknown/claude-haiku-4-5",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/claude-haiku-4-5-20251001",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 63.6,
        "benchmark_llmstats_tau2_retail": 83.2,
        "benchmark_llmstats_tau2_telecom": 83,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-mythos-preview",
        "source_name": "Claude Mythos Preview",
        "original_source_name": null,
        "canonical_name": "Claude Mythos Preview",
        "family_id": "anthropic/claude-mythos-preview",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 2,
        "category_score": 56.1,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 86.9,
        "benchmark_gpqa": 94.6,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 93.2,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 11.5,
        "benchmark_llmstats_hle": 64.7,
        "benchmark_llmstats_humanity_s_last_exam": 64.7,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 92.7,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 87.3,
        "benchmark_llmstats_swe_bench_pro": 77.8,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 82,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 41.4,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 93.9
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-1-20250805",
        "source_name": "Claude Opus 4.1",
        "original_source_name": "24Claude Opus 4.1",
        "canonical_name": "Claude Opus 4.1",
        "family_id": "unknown/claude-opus-4-1",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-1-20250805",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 56,
        "benchmark_llmstats_tau_bench_retail": 82.4,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-20250514",
        "source_name": "Claude Opus 4",
        "original_source_name": "18Claude Opus 4",
        "canonical_name": "Claude Opus 4",
        "family_id": "unknown/claude-opus-4",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-20250514",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 59.6,
        "benchmark_llmstats_tau_bench_retail": 81.4,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-5-20251101",
        "source_name": "Claude Opus 4.5",
        "original_source_name": "3Claude Opus 4.5",
        "canonical_name": "Claude Opus 4.5",
        "family_id": "unknown/claude-opus-4-5",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-5-20251101",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": 88.9,
        "benchmark_llmstats_tau2_telecom": 98.2,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-6",
        "source_name": "Claude Opus 4.6",
        "original_source_name": null,
        "canonical_name": "Claude Opus 4.6",
        "family_id": "anthropic/claude-opus-4-6",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 11,
        "category_score": 46.4,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
        "benchmark_aime_2025": 99.8,
        "benchmark_arc_agi_v2": 68.8,
        "benchmark_browsecomp": 84,
        "benchmark_gpqa": 91.3,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 77.4,
        "benchmark_llmstats_deepsearchqa": 91.3,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 32.1,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 56,
        "benchmark_llmstats_gdpval_aa": 53.5,
        "benchmark_llmstats_health": 6.3,
        "benchmark_llmstats_hle": 53.1,
        "benchmark_llmstats_humanity_s_last_exam": 53.1,
        "benchmark_llmstats_legal": 29.6,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 91.1,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 77.3,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": 72.7,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 77.8,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": 91.9,
        "benchmark_llmstats_tau2_telecom": 99.3,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 65.4,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 27.9,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 62.7,
        "benchmark_mrcr_v2": 76,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 80.8
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-7",
        "source_name": "Claude Opus 4.7",
        "original_source_name": null,
        "canonical_name": "Claude Opus 4.7",
        "family_id": "anthropic/claude-opus-4-7",
        "provider": "Anthropic",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 12,
        "category_score": 45.6,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 79.3,
        "benchmark_gpqa": 94.2,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 91,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 34.2,
        "benchmark_llmstats_frontiercode_1_1": 38.5,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 63,
        "benchmark_llmstats_gdpval_aa": 51.4,
        "benchmark_llmstats_health": 23.9,
        "benchmark_llmstats_hle": 54.7,
        "benchmark_llmstats_humanity_s_last_exam": 54.7,
        "benchmark_llmstats_legal": 31.7,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 91.5,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 64.3,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 69.4,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 34.5,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 77.3,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 87.6
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-4-8",
        "source_name": "Claude Opus 4.8",
        "original_source_name": null,
        "canonical_name": "Claude Opus 4.8",
        "family_id": "anthropic/claude-opus-4-8",
        "provider": "Anthropic",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 5,
        "category_score": 52.6,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 84.3,
        "benchmark_gpqa": 93.6,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 89.9,
        "benchmark_llmstats_deepsearchqa": 93.1,
        "benchmark_llmstats_deepswe_1_1": 59,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 32.3,
        "benchmark_llmstats_frontiercode_1_1": 46.5,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 75,
        "benchmark_llmstats_gdpval_aa": 54.6,
        "benchmark_llmstats_health": 19.5,
        "benchmark_llmstats_hle": 57.9,
        "benchmark_llmstats_humanity_s_last_exam": 57.9,
        "benchmark_llmstats_legal": 30.7,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 87.9,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 84.4,
        "benchmark_llmstats_swe_bench_pro": 69.2,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 74.6,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 59.9,
        "benchmark_llmstats_vision": 40.1,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 82.2,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 88.6
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-opus-5",
        "source_name": "Claude Opus 5",
        "original_source_name": null,
        "canonical_name": "Claude Opus 5",
        "family_id": "anthropic/claude-opus-5",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/claude-opus-5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 90.8,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 68.8,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 53.4,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 62,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 64.7,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-sonnet-4-20250514",
        "source_name": "Claude Sonnet 4",
        "original_source_name": "21Claude Sonnet 4",
        "canonical_name": "Claude Sonnet 4",
        "family_id": "unknown/claude-sonnet-4",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-20250514",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 60,
        "benchmark_llmstats_tau_bench_retail": 80.5,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-sonnet-4-5-20250929",
        "source_name": "Claude Sonnet 4.5",
        "original_source_name": "5Claude Sonnet 4.5",
        "canonical_name": "Claude Sonnet 4.5",
        "family_id": "unknown/claude-sonnet-4-5",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-5-20250929",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": 47.5,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 70,
        "benchmark_llmstats_tau_bench_retail": 86.2,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-sonnet-4-6",
        "source_name": "Claude Sonnet 4.6",
        "original_source_name": null,
        "canonical_name": "Claude Sonnet 4.6",
        "family_id": "anthropic/claude-sonnet-4-6",
        "provider": "Anthropic",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 28,
        "category_score": 38.4,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": 58.3,
        "benchmark_browsecomp": 74.7,
        "benchmark_gpqa": 89.9,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 32,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 15.9,
        "benchmark_llmstats_hle": 49,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 27.9,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 89.3,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 75.6,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": 72.5,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": 91.7,
        "benchmark_llmstats_tau2_telecom": 97.9,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 25.8,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 61.3,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 79.6
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "claude-sonnet-5",
        "source_name": "Claude Sonnet 5",
        "original_source_name": null,
        "canonical_name": "Claude Sonnet 5",
        "family_id": "anthropic/claude-sonnet-5",
        "provider": "Anthropic",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 84.7,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 54,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 42.7,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 53.9,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 78.3,
        "benchmark_llmstats_swe_bench_pro": 63.2,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 80.4,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 54.3,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 85.2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "deepseek-v4-flash-max",
        "source_name": "DeepSeek-V4-Flash-Max",
        "original_source_name": null,
        "canonical_name": "DeepSeek-V4-Flash-Max",
        "family_id": "deepseek/deepseek-v4-flash",
        "provider": "DeepSeek",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "category_rank": 25,
        "category_score": 39.7,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 73.2,
        "benchmark_gpqa": 88.1,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 28.3,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 28.1,
        "benchmark_llmstats_hle": 45.1,
        "benchmark_llmstats_humanity_s_last_exam": 45.1,
        "benchmark_llmstats_legal": 28.3,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 86.2,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": 34.1,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 52.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 47.8,
        "benchmark_llmstats_vision": 21.2,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 69,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 79
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "deepseek-v4-pro-max",
        "source_name": "DeepSeek-V4-Pro-Max",
        "original_source_name": null,
        "canonical_name": "DeepSeek-V4-Pro-Max",
        "family_id": "deepseek/deepseek-v4-pro",
        "provider": "DeepSeek",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "category_rank": 14,
        "category_score": 44,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 83.4,
        "benchmark_gpqa": 90.1,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 31.1,
        "benchmark_llmstats_frontiercode_1_1": 17.6,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 29,
        "benchmark_llmstats_gdpval_aa": 44.4,
        "benchmark_llmstats_health": 31.3,
        "benchmark_llmstats_hle": 48.2,
        "benchmark_llmstats_humanity_s_last_exam": 48.2,
        "benchmark_llmstats_legal": 31.1,
        "benchmark_llmstats_livecodebench": 93.5,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 87.5,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": 57.9,
        "benchmark_llmstats_swe_bench_multilingual": 76.2,
        "benchmark_llmstats_swe_bench_pro": 55.4,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 67.9,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 51.8,
        "benchmark_llmstats_vision": 23,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 73.6,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 80.6
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-2.5-pro",
        "source_name": "Gemini 2.5 Pro",
        "original_source_name": "29Gemini 2.5 Pro",
        "canonical_name": "Gemini 2.5 Pro",
        "family_id": "google/gemini-2-5-pro",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gemini-2.5-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-3-flash-preview",
        "source_name": "Gemini 3 Flash",
        "original_source_name": null,
        "canonical_name": "Gemini 3 Flash",
        "family_id": "google/gemini-3-flash",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 29,
        "category_score": 37.7,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
        "benchmark_aime_2025": 99.7,
        "benchmark_arc_agi_v2": 33.6,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 90.4,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 80.3,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 19,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 31.3,
        "benchmark_llmstats_hle": 43.5,
        "benchmark_llmstats_humanity_s_last_exam": 43.5,
        "benchmark_llmstats_legal": 12,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 91.8,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 81.2,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 69.1,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": 68.7,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 49.4,
        "benchmark_llmstats_vision": 26.2,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 57.4,
        "benchmark_mrcr_v2": 22.1,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 78
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-3-pro-preview",
        "source_name": "Gemini 3 Pro",
        "original_source_name": null,
        "canonical_name": "Gemini 3 Pro",
        "family_id": "google/gemini-3-pro",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 27,
        "category_score": 39.1,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
        "benchmark_aime_2025": 100,
        "benchmark_arc_agi_v2": 31.1,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 91.9,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 81.4,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 34.8,
        "benchmark_llmstats_hle": 45.8,
        "benchmark_llmstats_humanity_s_last_exam": 45.8,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 91.8,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 81,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 72.7,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": 72.1,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 27.1,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": 26.3,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 76.2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-3.1-pro-preview",
        "source_name": "Gemini 3.1 Pro",
        "original_source_name": null,
        "canonical_name": "Gemini 3.1 Pro",
        "family_id": "google/gemini-3-1-pro-preview",
        "provider": "Google",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 18,
        "category_score": 43.6,
        "match_status": "matched_manual",
        "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": 77.1,
        "benchmark_browsecomp": 85.9,
        "benchmark_gpqa": 94.3,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": 33.5,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 12,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 19.6,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 40,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 18.2,
        "benchmark_llmstats_hle": 51.4,
        "benchmark_llmstats_humanity_s_last_exam": 51.4,
        "benchmark_llmstats_legal": 15.3,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 92.6,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 80.5,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 54.2,
        "benchmark_llmstats_t2_bench": 99.3,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 68.5,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 31.7,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 69.2,
        "benchmark_mrcr_v2": 26.3,
        "benchmark_scicode": 59,
        "benchmark_swe_bench_verified": 80.6
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-3.5-flash",
        "source_name": "Gemini 3.5 Flash",
        "original_source_name": null,
        "canonical_name": "Gemini 3.5 Flash",
        "family_id": "google/gemini-3-5-flash",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gemini-3.5-flash",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 37,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 45.7,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 76.2,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 56.5,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 83.6,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemini-3.6-flash",
        "source_name": "Gemini 3.6 Flash",
        "original_source_name": null,
        "canonical_name": "Gemini 3.6 Flash",
        "family_id": "google/gemini-3-6-flash",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gemini-3.6-flash",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 49,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 47.4,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 58.7,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 78,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gemma-2-27b-it",
        "source_name": "Gemma 2 27B",
        "original_source_name": "26Gemma 2 27B",
        "canonical_name": "Gemma 2 27B",
        "family_id": "unknown/gemma-2-27b",
        "provider": "Google",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gemma-2-27b-it",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": 34.5,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "glm-4.5",
        "source_name": "GLM-4.5",
        "original_source_name": "20GLM-4.5",
        "canonical_name": "GLM-4.5",
        "family_id": "unknown/glm-4-5",
        "provider": "Z AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/glm-4.5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 60.4,
        "benchmark_llmstats_tau_bench_retail": 79.7,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "glm-4.5-air",
        "source_name": "GLM-4.5-Air",
        "original_source_name": "19GLM-4.5-Air",
        "canonical_name": "GLM-4.5-Air",
        "family_id": "unknown/glm-4-5-air",
        "provider": "Z AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/glm-4.5-air",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 60.8,
        "benchmark_llmstats_tau_bench_retail": 77.9,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "glm-5.1",
        "source_name": "GLM-5.1",
        "original_source_name": null,
        "canonical_name": "GLM-5.1",
        "family_id": "unknown/glm-5-1",
        "provider": "Z AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/glm-5.1",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 79.3,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 31,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 58.4,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 69,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 71.8,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "glm-5.2",
        "source_name": "GLM-5.2",
        "original_source_name": null,
        "canonical_name": "GLM-5.2",
        "family_id": "zai/glm-5-2",
        "provider": "ZAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 8,
        "category_score": 47.1,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/glm-5.2",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 91.2,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 44,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 24.5,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 74,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 54.7,
        "benchmark_llmstats_humanity_s_last_exam": 54.7,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 62.1,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 82.7,
        "benchmark_llmstats_toolathlon": 48.2,
        "benchmark_llmstats_vision": 28.4,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 76.8,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5-2025-08-07",
        "source_name": "GPT-5",
        "original_source_name": "10GPT-5",
        "canonical_name": "GPT-5",
        "family_id": "unknown/gpt-5",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5-2025-08-07",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 69.6,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 62.6,
        "benchmark_llmstats_tau2_retail": 81.1,
        "benchmark_llmstats_tau2_telecom": 96.7,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.1-2025-11-13",
        "source_name": "GPT-5.1",
        "original_source_name": null,
        "canonical_name": "GPT-5.1",
        "family_id": "openai/gpt-5-1",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 30,
        "category_score": 37.1,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
        "benchmark_aime_2025": 94,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 88.1,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": 26.7,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 31,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": 85.4,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 67,
        "benchmark_llmstats_tau2_retail": 77.9,
        "benchmark_llmstats_tau2_telecom": 95.6,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 21.7,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 76.3
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.1-instant-2025-11-12",
        "source_name": "GPT-5.1 Instant",
        "original_source_name": "12GPT-5.1 Instant",
        "canonical_name": "GPT-5.1 Instant",
        "family_id": "unknown/gpt-5-1-instant",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5.1-instant-2025-11-12",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 67,
        "benchmark_llmstats_tau2_retail": 77.9,
        "benchmark_llmstats_tau2_telecom": 95.6,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.1-thinking-2025-11-12",
        "source_name": "GPT-5.1 Thinking",
        "original_source_name": "11GPT-5.1 Thinking",
        "canonical_name": "GPT-5.1 Thinking",
        "family_id": "unknown/gpt-5-1-thinking",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5.1-thinking-2025-11-12",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 67,
        "benchmark_llmstats_tau2_retail": 77.9,
        "benchmark_llmstats_tau2_telecom": 95.6,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.2-2025-12-11",
        "source_name": "GPT-5.2",
        "original_source_name": null,
        "canonical_name": "GPT-5.2",
        "family_id": "openai/gpt-5-2",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 21,
        "category_score": 42.1,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
        "benchmark_aime_2025": 100,
        "benchmark_arc_agi_v2": 52.9,
        "benchmark_browsecomp": 65.8,
        "benchmark_gpqa": 92.4,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 82.1,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": 40.3,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 31.5,
        "benchmark_llmstats_hle": 34.5,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": 89.6,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 79.5,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 86.3,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": 82,
        "benchmark_llmstats_tau2_telecom": 98.7,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 46.3,
        "benchmark_llmstats_vision": 28.4,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 60.6,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 80
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.2-pro-2025-12-11",
        "source_name": "GPT-5.2 Pro",
        "original_source_name": null,
        "canonical_name": "GPT-5.2 Pro",
        "family_id": "openai/gpt-5-2-pro",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 19,
        "category_score": 43.2,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gpt-5.2-pro-2025-12-11",
        "benchmark_aime_2025": 100,
        "benchmark_arc_agi_v2": 54.2,
        "benchmark_browsecomp": 77.9,
        "benchmark_gpqa": 93.2,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 36.6,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 24.4,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.3-codex",
        "source_name": "GPT-5.3 Codex",
        "original_source_name": "20GPT-5.3 Codex",
        "canonical_name": "GPT-5.3 Codex",
        "family_id": "unknown/gpt-5-3-codex",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gpt-5.3-codex",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 77.3,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.4",
        "source_name": "GPT-5.4",
        "original_source_name": null,
        "canonical_name": "GPT-5.4",
        "family_id": "openai/gpt-5-4",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 17,
        "category_score": 43.7,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/gpt-5.4",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": 73.3,
        "benchmark_browsecomp": 82.7,
        "benchmark_gpqa": 92.8,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 52,
        "benchmark_llmstats_facts_grounding_default": 91.9,
        "benchmark_llmstats_finance": 27.6,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": 47.6,
        "benchmark_llmstats_frontierswe": 54,
        "benchmark_llmstats_gdpval_aa": 47.6,
        "benchmark_llmstats_health": 25.4,
        "benchmark_llmstats_hle": 39.8,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 24.2,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": 55.6,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 81.2,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": 22.8,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": 55.1,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": 29.8,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 57.7,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": 98.9,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 75.1,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 54.6,
        "benchmark_llmstats_vision": 30.1,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 67.2,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.5",
        "source_name": "GPT-5.5",
        "original_source_name": null,
        "canonical_name": "GPT-5.5",
        "family_id": "openai/gpt-5-5",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 7,
        "category_score": 49.1,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gpt-5.5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": 85,
        "benchmark_browsecomp": 84.4,
        "benchmark_gpqa": 93.6,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 67,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 28.9,
        "benchmark_llmstats_frontiercode_1_1": 43,
        "benchmark_llmstats_frontiermath": 35.4,
        "benchmark_llmstats_frontierswe": 73,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 52.2,
        "benchmark_llmstats_humanity_s_last_exam": 52.2,
        "benchmark_llmstats_legal": 21.1,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 83.2,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 58.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": 98,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 82.7,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 55.6,
        "benchmark_llmstats_vision": 36.9,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 75.3,
        "benchmark_mrcr_v2": 74,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.5-pro",
        "source_name": "GPT-5.5 Pro",
        "original_source_name": "25GPT-5.5 Pro",
        "canonical_name": "GPT-5.5 Pro",
        "family_id": "unknown/gpt-5-5-pro",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/gpt-5.5-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 90.1,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 57.2,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.6-luna",
        "source_name": "GPT-5.6 Luna",
        "original_source_name": null,
        "canonical_name": "GPT-5.6 Luna",
        "family_id": "openai/gpt-5-6-luna",
        "provider": "OpenAI",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 9,
        "category_score": 46.8,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 83.3,
        "benchmark_gpqa": 92.3,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 67,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 26.7,
        "benchmark_llmstats_frontiercode_1_1": 39.8,
        "benchmark_llmstats_frontiermath": 78.6,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 53.1,
        "benchmark_llmstats_health": 28.7,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 27.9,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 78.4,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 62.7,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 84.7,
        "benchmark_llmstats_toolathlon": 53.4,
        "benchmark_llmstats_vision": 23.5,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": 41.3,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.6-sol",
        "source_name": "GPT-5.6 Sol",
        "original_source_name": null,
        "canonical_name": "GPT-5.6 Sol",
        "family_id": "openai/gpt-5-6-sol",
        "provider": "OpenAI",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 1,
        "category_score": 58,
        "match_status": "matched_manual",
        "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 90.4,
        "benchmark_gpqa": 94.6,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 73,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 37.1,
        "benchmark_llmstats_frontiercode_1_1": 47.5,
        "benchmark_llmstats_frontiermath": 89,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 58.3,
        "benchmark_llmstats_health": 36.7,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 32.4,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 83,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 64.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 88.8,
        "benchmark_llmstats_toolathlon": 58,
        "benchmark_llmstats_vision": 38.2,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": 91.5,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "gpt-5.6-terra",
        "source_name": "GPT-5.6 Terra",
        "original_source_name": null,
        "canonical_name": "GPT-5.6 Terra",
        "family_id": "openai/gpt-5-6-terra",
        "provider": "OpenAI",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 4,
        "category_score": 53.3,
        "match_status": "matched_manual",
        "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 87.5,
        "benchmark_gpqa": 92.9,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 70,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 31.7,
        "benchmark_llmstats_frontiercode_1_1": 41.3,
        "benchmark_llmstats_frontiermath": 84.9,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 53.1,
        "benchmark_llmstats_health": 32.4,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 28.5,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 80.7,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 63.4,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 87.4,
        "benchmark_llmstats_toolathlon": 53.1,
        "benchmark_llmstats_vision": 30,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": 89.6,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "grok-4-heavy",
        "source_name": "Grok-4 Heavy",
        "original_source_name": null,
        "canonical_name": "Grok-4 Heavy",
        "family_id": "xai/grok-4-heavy",
        "provider": "xAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 22,
        "category_score": 41.4,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/grok-4-heavy",
        "benchmark_aime_2025": 100,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 88.4,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 50.7,
        "benchmark_llmstats_humanity_s_last_exam": 50.7,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 24.9,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "grok-4.5",
        "source_name": "Grok 4.5",
        "original_source_name": null,
        "canonical_name": "Grok 4.5",
        "family_id": "xai/grok-4-5",
        "provider": "xAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 6,
        "category_score": 49.5,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/grok-4.5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 93,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 54,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 27.3,
        "benchmark_llmstats_frontiercode_1_1": 42.4,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 51.4,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 27.3,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 64.7,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 83.3,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "hermes-3-70b",
        "source_name": "Hermes 3 70B",
        "original_source_name": "14Hermes 3 70B",
        "canonical_name": "Hermes 3 70B",
        "family_id": "unknown/hermes-3-70b",
        "provider": "Nous Research",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/hermes-3-70b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": 89.9,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "hy3",
        "source_name": "Hy3",
        "original_source_name": null,
        "canonical_name": "Hy3",
        "family_id": "tencent/hy3",
        "provider": "Tencent",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "category_rank": 15,
        "category_score": 43.8,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/hy3",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 84.2,
        "benchmark_gpqa": 90.4,
        "benchmark_llmstats_aa_lcr": 73.4,
        "benchmark_llmstats_apex_agents": 25.6,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": 91,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 75.8,
        "benchmark_llmstats_swe_bench_pro": 57.9,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 71.7,
        "benchmark_llmstats_toolathlon": 48.5,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": 76.4,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 79.1,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 78
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "kimi-k2-thinking-0905",
        "source_name": "Kimi K2-Thinking-0905",
        "original_source_name": "21Kimi K2-Thinking-0905",
        "canonical_name": "Kimi K2-Thinking-0905",
        "family_id": "unknown/kimi-k2-thinking-0905",
        "provider": "Moonshot AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/kimi-k2-thinking-0905",
        "benchmark_aime_2025": 100,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 51,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 84.6,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "kimi-k2.5",
        "source_name": "Kimi K2.5",
        "original_source_name": "29Kimi K2.5",
        "canonical_name": "Kimi K2.5",
        "family_id": "unknown/kimi-k2-5",
        "provider": "Moonshot AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/kimi-k2.5",
        "benchmark_aime_2025": 96.1,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 74.9,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 70,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": 77.1,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 50.2,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 61,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 75.9,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 87.1,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": 57.4,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": 79,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "kimi-k2.6",
        "source_name": "Kimi K2.6",
        "original_source_name": null,
        "canonical_name": "Kimi K2.6",
        "family_id": "moonshot-ai/kimi-k2-6",
        "provider": "MoonshotAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 13,
        "category_score": 44.7,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 86.3,
        "benchmark_gpqa": 90.5,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": 27.9,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 86.7,
        "benchmark_llmstats_deepsearchqa": 83,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 24.5,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 27,
        "benchmark_llmstats_gdpval_aa": 40.1,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 36.4,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 19.9,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": 89.6,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 80.1,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 76.7,
        "benchmark_llmstats_swe_bench_pro": 58.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 66.7,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 50,
        "benchmark_llmstats_vision": 30.4,
        "benchmark_llmstats_widesearch": 80.8,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": 52.2,
        "benchmark_swe_bench_verified": 80.2
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "kimi-k2.7-code",
        "source_name": "Kimi K2.7 Code",
        "original_source_name": null,
        "canonical_name": "Kimi K2.7 Code",
        "family_id": "kimi/kimi-k2-7-code",
        "provider": "Kimi",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/kimi-k2.7-code",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 31,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 30.1,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 76,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "kimi-k3",
        "source_name": "Kimi K3",
        "original_source_name": null,
        "canonical_name": "Kimi K3",
        "family_id": "kimi/kimi-k3",
        "provider": "MoonshotAI",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 3,
        "category_score": 55.7,
        "match_status": "matched_manual",
        "source_model_url": "https://llm-stats.com/models/kimi-k3",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 91.2,
        "benchmark_gpqa": 93.5,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": 37.6,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 91.3,
        "benchmark_llmstats_deepsearchqa": 95,
        "benchmark_llmstats_deepswe_1_1": 69,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 31.5,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": 81.2,
        "benchmark_llmstats_gdpval_aa": 55.6,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": 56,
        "benchmark_llmstats_humanity_s_last_exam": 56,
        "benchmark_llmstats_legal": 31.5,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 81.6,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 88.3,
        "benchmark_llmstats_toolathlon": 73.2,
        "benchmark_llmstats_vision": 39.2,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 84.2,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "llama-3.1-405b-instruct",
        "source_name": "Llama 3.1 405B Instruct",
        "original_source_name": "8Llama 3.1 405B Instruct",
        "canonical_name": "Llama 3.1 405B Instruct",
        "family_id": "unknown/llama-3-1-405b-instruct",
        "provider": "Meta",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/llama-3.1-405b-instruct",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "llama-3.1-70b-instruct",
        "source_name": "Llama 3.1 70B Instruct",
        "original_source_name": "29Llama 3.1 70B Instruct",
        "canonical_name": "Llama 3.1 70B Instruct",
        "family_id": "unknown/llama-3-1-70b-instruct",
        "provider": "Meta",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/llama-3.1-70b-instruct",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "longcat-flash-thinking",
        "source_name": "LongCat-Flash-Thinking",
        "original_source_name": "26LongCat-Flash-Thinking",
        "canonical_name": "LongCat-Flash-Thinking",
        "family_id": "unknown/longcat-flash-thinking",
        "provider": "Meituan",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/longcat-flash-thinking",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 67.5,
        "benchmark_llmstats_tau2_retail": 71.5,
        "benchmark_llmstats_tau2_telecom": 83.1,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "longcat-flash-thinking-2601",
        "source_name": "LongCat-Flash-Thinking-2601",
        "original_source_name": "2LongCat-Flash-Thinking-2601",
        "canonical_name": "LongCat-Flash-Thinking-2601",
        "family_id": "unknown/longcat-flash-thinking-2601",
        "provider": "Meituan",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/longcat-flash-thinking-2601",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 76.5,
        "benchmark_llmstats_tau2_retail": 88.6,
        "benchmark_llmstats_tau2_telecom": 99.3,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "mai-thinking-1",
        "source_name": "MAI-Thinking-1",
        "original_source_name": "22MAI-Thinking-1",
        "canonical_name": "MAI-Thinking-1",
        "family_id": "unknown/mai-thinking-1",
        "provider": "Microsoft",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/mai-thinking-1",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 61,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "mimo-v2-pro",
        "source_name": "MiMo-V2-Pro",
        "original_source_name": "23MiMo-V2-Pro",
        "canonical_name": "MiMo-V2-Pro",
        "family_id": "unknown/mimo-v2-pro",
        "provider": "Xiaomi",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/mimo-v2-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": 86.7,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": 96.8,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "mimo-v2.5-pro",
        "source_name": "MiMo-V2.5-Pro",
        "original_source_name": null,
        "canonical_name": "MiMo-V2.5-Pro",
        "family_id": "xiaomi/mimo-v2-5-pro",
        "provider": "Xiaomi",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/mimo-v2.5-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 57.2,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 68.4,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 78.9
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "minimax-m1-40k",
        "source_name": "MiniMax M1 40K",
        "original_source_name": "13MiniMax M1 40K",
        "canonical_name": "MiniMax M1 40K",
        "family_id": "unknown/minimax-m1-40k",
        "provider": "MiniMax",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/minimax-m1-40k",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 61,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "minimax-m1-80k",
        "source_name": "MiniMax M1 80K",
        "original_source_name": "18MiniMax M1 80K",
        "canonical_name": "MiniMax M1 80K",
        "family_id": "unknown/minimax-m1-80k",
        "provider": "MiniMax",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/minimax-m1-80k",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 61.5,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "minimax-m2.5",
        "source_name": "MiniMax M2.5",
        "original_source_name": "29MiniMax M2.5",
        "canonical_name": "MiniMax M2.5",
        "family_id": "unknown/minimax-m2-5",
        "provider": "MiniMax",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/minimax-m2.5",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 76.3,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "minimax-m3",
        "source_name": "MiniMax M3",
        "original_source_name": null,
        "canonical_name": "MiniMax M3",
        "family_id": "minimax/minimax-m3",
        "provider": "MiniMax",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/minimax-m3",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 83.5,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": 14.7,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 47.7,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 59,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 66,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 74.2,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 80.5
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "mistral-small-latest",
        "source_name": "Mistral Small 4",
        "original_source_name": "12Mistral Small 4",
        "canonical_name": "Mistral Small 4",
        "family_id": "mistral-ai/mistral-small-4",
        "provider": "Mistral AI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/mistral-small-latest",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 71.2,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "muse-spark",
        "source_name": "Muse Spark",
        "original_source_name": null,
        "canonical_name": "Muse Spark",
        "family_id": "meta/muse-spark",
        "provider": "Meta",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 20,
        "category_score": 42.5,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/muse-spark",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": 42.5,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 89.5,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 86.4,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 17.9,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 36.5,
        "benchmark_llmstats_hle": 58.4,
        "benchmark_llmstats_humanity_s_last_exam": 58.4,
        "benchmark_llmstats_legal": 17.9,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 80.4,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 84.1,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 52.4,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 33.3,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 77.4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "muse-spark-1.1",
        "source_name": "Muse Spark 1.1",
        "original_source_name": null,
        "canonical_name": "Muse Spark 1.1",
        "family_id": "unknown/muse-spark-1-1",
        "provider": "Baidu",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": 53,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 62.1,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 61.5,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 80,
        "benchmark_llmstats_toolathlon": 75.6,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 88.1,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "nemotron-3-ultra-550b-a55b",
        "source_name": "Nemotron 3 Ultra (550B A55B)",
        "original_source_name": "15Nemotron 3 Ultra (550B A55B)",
        "canonical_name": "Nemotron 3 Ultra (550B A55B)",
        "family_id": "unknown/nemotron-3-ultra-550b-a55b",
        "provider": "NVIDIA",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/nemotron-3-ultra-550b-a55b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 65.4,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 61.9,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "nova-2-lite",
        "source_name": "Nova 2 Lite",
        "original_source_name": "16Nova 2 Lite",
        "canonical_name": "Nova 2 Lite",
        "family_id": "unknown/nova-2-lite",
        "provider": "Amazon",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/nova-2-lite",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 76.6,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 64.8,
        "benchmark_llmstats_tau2_retail": 76.5,
        "benchmark_llmstats_tau2_telecom": 76,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "nova-2-omni",
        "source_name": "Nova 2 Omni",
        "original_source_name": "9Nova 2 Omni",
        "canonical_name": "Nova 2 Omni",
        "family_id": "unknown/nova-2-omni",
        "provider": "Amazon",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/nova-2-omni",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 75.5,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 68.8,
        "benchmark_llmstats_tau2_retail": 78.3,
        "benchmark_llmstats_tau2_telecom": 80,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "nova-2-pro",
        "source_name": "Nova 2 Pro",
        "original_source_name": "8Nova 2 Pro",
        "canonical_name": "Nova 2 Pro",
        "family_id": "unknown/nova-2-pro",
        "provider": "Amazon",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/nova-2-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 77.7,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 65.2,
        "benchmark_llmstats_tau2_retail": 77.7,
        "benchmark_llmstats_tau2_telecom": 92.7,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "o3-2025-04-16",
        "source_name": "o3",
        "original_source_name": "27o3",
        "canonical_name": "o3",
        "family_id": "openai/o3",
        "provider": "OpenAI",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/o3-2025-04-16",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 60.4,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": 64.8,
        "benchmark_llmstats_tau2_retail": 80.2,
        "benchmark_llmstats_tau2_telecom": 58.2,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen-2.5-72b-instruct",
        "source_name": "Qwen2.5 72B Instruct",
        "original_source_name": "22Qwen2.5 72B Instruct",
        "canonical_name": "Qwen2.5 72B Instruct",
        "family_id": "unknown/qwen2-5-72b-instruct",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/qwen-2.5-72b-instruct",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": 93.5,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3-coder-480b-a35b-instruct",
        "source_name": "Qwen3-Coder 480B A35B Instruct",
        "original_source_name": "29Qwen3-Coder 480B A35B Instruct",
        "canonical_name": "Qwen3-Coder 480B A35B Instruct",
        "family_id": "unknown/qwen3-coder-480b-a35b-instruct",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/qwen3-coder-480b-a35b-instruct",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": 60,
        "benchmark_llmstats_tau_bench_retail": 77.5,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3-vl-235b-a22b-thinking",
        "source_name": "Qwen3 VL 235B A22B Thinking",
        "original_source_name": "28Qwen3 VL 235B A22B Thinking",
        "canonical_name": "Qwen3 VL 235B A22B Thinking",
        "family_id": "unknown/qwen3-vl-235b-a22b-thinking",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "ambiguous",
        "source_model_url": "https://llm-stats.com/models/qwen3-vl-235b-a22b-thinking",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": 8.5,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": 79.1,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": 86.7,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.5-122b-a10b",
        "source_name": "Qwen3.5-122B-A10B",
        "original_source_name": "30Qwen3.5-122B-A10B",
        "canonical_name": "Qwen3.5-122B-A10B",
        "family_id": "unknown/qwen3-5-122b-a10b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.5-122b-a10b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 66.9,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": 69.9,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 47.5,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 60.2,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 74.4,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 86.7,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": 44.1,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": 60.5,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.5-27b",
        "source_name": "Qwen3.5-27B",
        "original_source_name": "14Qwen3.5-27B",
        "canonical_name": "Qwen3.5-27B",
        "family_id": "unknown/qwen3-5-27b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.5-27b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 66.1,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 60.6,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 73.6,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.5-35b-a3b",
        "source_name": "Qwen3.5-35B-A3B",
        "original_source_name": "20Qwen3.5-35B-A3B",
        "canonical_name": "Qwen3.5-35B-A3B",
        "family_id": "unknown/qwen3-5-35b-a3b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.5-35b-a3b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 58.5,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 59,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 71.4,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.5-397b-a17b",
        "source_name": "Qwen3.5-397B-A17B",
        "original_source_name": null,
        "canonical_name": "Qwen3.5-397B-A17B",
        "family_id": "alibaba/qwen3-5-397b-a17b",
        "provider": "Qwen",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "category_rank": 26,
        "category_score": 39.6,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 69,
        "benchmark_gpqa": 88.4,
        "benchmark_llmstats_aa_lcr": 68.7,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": 70.3,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 31.8,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 38.7,
        "benchmark_llmstats_hle": 28.7,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 31.8,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 63.2,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 87.8,
        "benchmark_llmstats_mmmlu": 88.5,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": 67.6,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": 46.9,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 38.3,
        "benchmark_llmstats_vision": 19.6,
        "benchmark_llmstats_widesearch": 74,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 76.4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.5-9b",
        "source_name": "Qwen3.5-9B",
        "original_source_name": "27Qwen3.5-9B",
        "canonical_name": "Qwen3.5-9B",
        "family_id": "unknown/qwen3-5-9b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.5-9b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": 63,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 55.2,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.6-27b",
        "source_name": "Qwen3.6-27B",
        "original_source_name": "28Qwen3.6-27B",
        "canonical_name": "Qwen3.6-27B",
        "family_id": "unknown/qwen3-6-27b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.6-27b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.6-35b-a3b",
        "source_name": "Qwen3.6-35B-A3B",
        "original_source_name": "24Qwen3.6-35B-A3B",
        "canonical_name": "Qwen3.6-35B-A3B",
        "family_id": "unknown/qwen3-6-35b-a3b",
        "provider": "Alibaba",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "identity_unresolved",
        "source_model_url": "https://llm-stats.com/models/qwen3.6-35b-a3b",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 71.4,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.6-plus",
        "source_name": "Qwen3.6 Plus",
        "original_source_name": null,
        "canonical_name": "Qwen3.6 Plus",
        "family_id": "alibaba/qwen3-6-plus",
        "provider": "Qwen",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 23,
        "category_score": 40.4,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 90.4,
        "benchmark_llmstats_aa_lcr": 68.3,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 81.5,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 33,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 41.6,
        "benchmark_llmstats_hle": 28.8,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 34.7,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": 62,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 88.5,
        "benchmark_llmstats_mmmlu": 89.5,
        "benchmark_llmstats_mmmu": 86,
        "benchmark_llmstats_mmmu_pro": 78.8,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 68.2,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 56.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": 39.8,
        "benchmark_llmstats_vision": 29.7,
        "benchmark_llmstats_widesearch": 74.3,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 74.1,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 78.8
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.7-max",
        "source_name": "Qwen3.7 Max",
        "original_source_name": null,
        "canonical_name": "Qwen3.7 Max",
        "family_id": "alibaba/qwen3-7",
        "provider": "Qwen",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 10,
        "category_score": 46.7,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/qwen3.7-max",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 92.4,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 37.5,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": 43.6,
        "benchmark_llmstats_health": 45.1,
        "benchmark_llmstats_hle": 41.4,
        "benchmark_llmstats_humanity_s_last_exam": 41.4,
        "benchmark_llmstats_legal": 38.4,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": 91.6,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 89.6,
        "benchmark_llmstats_mmmlu": 90.3,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 78.3,
        "benchmark_llmstats_swe_bench_pro": 60.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 69.7,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 26,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 76.4,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": 53.5,
        "benchmark_swe_bench_verified": 80.4
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "qwen3.7-plus",
        "source_name": "Qwen3.7-Plus",
        "original_source_name": null,
        "canonical_name": "Qwen3.7-Plus",
        "family_id": "alibaba/qwen3-7-plus",
        "provider": "Qwen",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "category_rank": 15,
        "category_score": 43.8,
        "match_status": "matched_family",
        "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": null,
        "benchmark_gpqa": 90.3,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": 85.9,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": 31.4,
        "benchmark_llmstats_frontiercode_1_1": 10.2,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": 41.7,
        "benchmark_llmstats_hle": 34.7,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": 33,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": 89.6,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 76.2,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": 88.5,
        "benchmark_llmstats_mmmlu": 89,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": 79,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": 79,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": 75.8,
        "benchmark_llmstats_swe_bench_pro": 57.6,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": 70.3,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": 34.4,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 73.2,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": 51.3,
        "benchmark_swe_bench_verified": 77.7
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "seed-2.0-pro",
        "source_name": "Seed 2.0 Pro",
        "original_source_name": null,
        "canonical_name": "Seed 2.0 Pro",
        "family_id": "bytedance/seed-2-0-pro",
        "provider": "Bytedance",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": 24,
        "category_score": 40.3,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
        "benchmark_aime_2025": 98.3,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 77.3,
        "benchmark_gpqa": 88.9,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": null,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": null,
        "benchmark_llmstats_mathvista": null,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": null,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": null,
        "benchmark_llmstats_toolathlon": null,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": null,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": null,
        "benchmark_swe_bench_verified": 76.5
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "seed-2.1-pro",
        "source_name": "Seed 2.1 Pro",
        "original_source_name": null,
        "canonical_name": "Seed 2.1 Pro",
        "family_id": "unknown/seed-2-1-pro",
        "provider": "ByteDance",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 86.2,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 55.7,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 78,
        "benchmark_llmstats_mathvista": 90.7,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 57.5,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 71,
        "benchmark_llmstats_toolathlon": 50.6,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 83.8,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": 59.8,
        "benchmark_swe_bench_verified": null
      },
      {
        "schema_version": "powerbi-v2-wide",
        "snapshot_date": "2026-07-26",
        "source": "LLMStats",
        "capability": "general",
        "source_model_id": "seed-2.1-turbo",
        "source_name": "Seed 2.1 Turbo",
        "original_source_name": null,
        "canonical_name": "Seed 2.1 Turbo",
        "family_id": "unknown/seed-2-1-turbo",
        "provider": "ByteDance",
        "availability_class": "unknown",
        "is_open_weights": null,
        "category_rank": null,
        "category_score": null,
        "match_status": "source_missing",
        "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
        "benchmark_aime_2025": null,
        "benchmark_arc_agi_v2": null,
        "benchmark_browsecomp": 84.9,
        "benchmark_gpqa": null,
        "benchmark_llmstats_aa_lcr": null,
        "benchmark_llmstats_apex_agents": null,
        "benchmark_llmstats_browsecomp_zh": null,
        "benchmark_llmstats_charxiv_r": null,
        "benchmark_llmstats_deepsearchqa": null,
        "benchmark_llmstats_deepswe_1_1": null,
        "benchmark_llmstats_facts_grounding_default": null,
        "benchmark_llmstats_finance": null,
        "benchmark_llmstats_frontiercode_1_1": null,
        "benchmark_llmstats_frontiermath": null,
        "benchmark_llmstats_frontierswe": null,
        "benchmark_llmstats_gdpval_aa": null,
        "benchmark_llmstats_health": null,
        "benchmark_llmstats_hle": null,
        "benchmark_llmstats_humanity_s_last_exam": 54.6,
        "benchmark_llmstats_legal": null,
        "benchmark_llmstats_livecodebench": null,
        "benchmark_llmstats_livecodebench_v6": null,
        "benchmark_llmstats_longbench_v2": null,
        "benchmark_llmstats_longbench_v2_short": null,
        "benchmark_llmstats_lvbench": 76.8,
        "benchmark_llmstats_mathvista": 90.5,
        "benchmark_llmstats_mm_mt_bench": null,
        "benchmark_llmstats_mmlu_pro": null,
        "benchmark_llmstats_mmmlu": null,
        "benchmark_llmstats_mmmu": null,
        "benchmark_llmstats_mmmu_pro": null,
        "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
        "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
        "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
        "benchmark_llmstats_mt_bench": null,
        "benchmark_llmstats_multi_challenge": null,
        "benchmark_llmstats_multi_if": null,
        "benchmark_llmstats_natural_questions": null,
        "benchmark_llmstats_osworld": null,
        "benchmark_llmstats_screenspot_pro": null,
        "benchmark_llmstats_seal_0": null,
        "benchmark_llmstats_simpleqa": null,
        "benchmark_llmstats_swe_bench_multilingual": null,
        "benchmark_llmstats_swe_bench_pro": 57,
        "benchmark_llmstats_t2_bench": null,
        "benchmark_llmstats_tau2_airline": null,
        "benchmark_llmstats_tau2_retail": null,
        "benchmark_llmstats_tau2_telecom": null,
        "benchmark_llmstats_tau_bench_airline": null,
        "benchmark_llmstats_tau_bench_retail": null,
        "benchmark_llmstats_terminal_bench_2_0": null,
        "benchmark_llmstats_terminal_bench_2_1": 67.6,
        "benchmark_llmstats_toolathlon": 49.1,
        "benchmark_llmstats_vision": null,
        "benchmark_llmstats_widesearch": null,
        "benchmark_llmstats_writingbench": null,
        "benchmark_mcp_atlas": 80.3,
        "benchmark_mrcr_v2": null,
        "benchmark_scicode": 57.8,
        "benchmark_swe_bench_verified": null
      }
    ],
    "capabilities": {
      "coding": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-fable-5",
          "source_name": "Claude Fable 5",
          "original_source_name": null,
          "canonical_name": "Claude Fable 5",
          "family_id": "anthropic/claude-fable-5",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 2,
          "category_score": 48.4,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/claude-fable-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 70,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 53.5,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 90,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 80,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 84.3,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 95
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 3,
          "category_score": 46.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 87.3,
          "benchmark_llmstats_swe_bench_pro": 77.8,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 82,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 93.9
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 35.1,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 56,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 77.8,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 65.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 62.7,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.8
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 12,
          "category_score": 39.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 38.5,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 63,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.3,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 69.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 77.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 87.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 6,
          "category_score": 43.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 59,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 46.5,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 75,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 84.4,
          "benchmark_llmstats_swe_bench_pro": 69.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 74.6,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 82.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 88.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-opus-5",
          "source_name": "Claude Opus 5",
          "original_source_name": null,
          "canonical_name": "Claude Opus 5",
          "family_id": "anthropic/claude-opus-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 42.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-opus-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 68.8,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 53.4,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 33,
          "category_score": 27.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 61.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 79.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "claude-sonnet-5",
          "source_name": "Claude Sonnet 5",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 5",
          "family_id": "anthropic/claude-sonnet-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 40.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 54,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 42.7,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 78.3,
          "benchmark_llmstats_swe_bench_pro": 63.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 80.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 85.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 31,
          "category_score": 29.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 52.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 69,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 79
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 23,
          "category_score": 33.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 17.6,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 29,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": 93.5,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 76.2,
          "benchmark_llmstats_swe_bench_pro": 55.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 67.9,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 73.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gemini-3-flash-preview",
          "source_name": "Gemini 3 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Flash",
          "family_id": "google/gemini-3-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 38,
          "category_score": 22.8,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 57.4,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gemini-3-pro-preview",
          "source_name": "Gemini 3 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Pro",
          "family_id": "google/gemini-3-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 35,
          "category_score": 24.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 25,
          "category_score": 33,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 12,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 40,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 54.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 68.5,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 69.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 59,
          "benchmark_swe_bench_verified": 80.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gemini-3.5-flash",
          "source_name": "Gemini 3.5 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.5 Flash",
          "family_id": "google/gemini-3-5-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 34.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.5-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 37,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 76.2,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 83.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gemini-3.6-flash",
          "source_name": "Gemini 3.6 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.6 Flash",
          "family_id": "google/gemini-3-6-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 26,
          "category_score": 32.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.6-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 49,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 78,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "glm-5.1",
          "source_name": "GLM-5.1",
          "original_source_name": null,
          "canonical_name": "GLM-5.1",
          "family_id": "unknown/glm-5-1",
          "provider": "Z AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 24,
          "category_score": 33.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/glm-5.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 31,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 69,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 71.8,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "glm-5.2",
          "source_name": "GLM-5.2",
          "original_source_name": null,
          "canonical_name": "GLM-5.2",
          "family_id": "zai/glm-5-2",
          "provider": "ZAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 39,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-5.2",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 44,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 24.5,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 74,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 62.1,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 82.7,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76.8,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 40,
          "category_score": 20.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.3
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 34,
          "category_score": 24.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 60.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 34.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 52,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 54,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 75.1,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 67.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 8,
          "category_score": 41.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 67,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 43,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 73,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 82.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 75.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 11,
          "category_score": 39.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 67,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 39.8,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 62.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 84.7,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 1,
          "category_score": 50.1,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 73,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 47.5,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 88.8,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 4,
          "category_score": 46,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 70,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 41.3,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 63.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 87.4,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "grok-4-heavy",
          "source_name": "Grok-4 Heavy",
          "original_source_name": null,
          "canonical_name": "Grok-4 Heavy",
          "family_id": "xai/grok-4-heavy",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 41,
          "category_score": 18.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4-heavy",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "grok-4.5",
          "source_name": "Grok 4.5",
          "original_source_name": null,
          "canonical_name": "Grok 4.5",
          "family_id": "xai/grok-4-5",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 9,
          "category_score": 40.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 54,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 42.4,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 83.3,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 17,
          "category_score": 35.7,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 75.8,
          "benchmark_llmstats_swe_bench_pro": 57.9,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 71.7,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 79.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "kimi-k2.6",
          "source_name": "Kimi K2.6",
          "original_source_name": null,
          "canonical_name": "Kimi K2.6",
          "family_id": "moonshot-ai/kimi-k2-6",
          "provider": "MoonshotAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 19,
          "category_score": 35.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 27,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 76.7,
          "benchmark_llmstats_swe_bench_pro": 58.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 66.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 52.2,
          "benchmark_swe_bench_verified": 80.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "kimi-k2.7-code",
          "source_name": "Kimi K2.7 Code",
          "original_source_name": null,
          "canonical_name": "Kimi K2.7 Code",
          "family_id": "kimi/kimi-k2-7-code",
          "provider": "Kimi",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 32.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.7-code",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 31,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 30.1,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "kimi-k3",
          "source_name": "Kimi K3",
          "original_source_name": null,
          "canonical_name": "Kimi K3",
          "family_id": "kimi/kimi-k3",
          "provider": "MoonshotAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 5,
          "category_score": 44.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/kimi-k3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 69,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": 81.2,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 88.3,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 84.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "mimo-v2.5-pro",
          "source_name": "MiMo-V2.5-Pro",
          "original_source_name": null,
          "canonical_name": "MiMo-V2.5-Pro",
          "family_id": "xiaomi/mimo-v2-5-pro",
          "provider": "Xiaomi",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 32.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/mimo-v2.5-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 68.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78.9
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "minimax-m3",
          "source_name": "MiniMax M3",
          "original_source_name": null,
          "canonical_name": "MiniMax M3",
          "family_id": "minimax/minimax-m3",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 18,
          "category_score": 35.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/minimax-m3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 14.7,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 59,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 66,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 74.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.5
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 36,
          "category_score": 23.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 52.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 77.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "muse-spark-1.1",
          "source_name": "Muse Spark 1.1",
          "original_source_name": null,
          "canonical_name": "Muse Spark 1.1",
          "family_id": "unknown/muse-spark-1-1",
          "provider": "Baidu",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 38.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": 53,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 61.5,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 80,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 88.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 37,
          "category_score": 23.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 32,
          "category_score": 29.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 56.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 74.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78.8
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "qwen3.7-max",
          "source_name": "Qwen3.7 Max",
          "original_source_name": null,
          "canonical_name": "Qwen3.7 Max",
          "family_id": "alibaba/qwen3-7",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 14,
          "category_score": 38.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 78.3,
          "benchmark_llmstats_swe_bench_pro": 60.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 69.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76.4,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 53.5,
          "benchmark_swe_bench_verified": 80.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "qwen3.7-plus",
          "source_name": "Qwen3.7-Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.7-Plus",
          "family_id": "alibaba/qwen3-7-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 28,
          "category_score": 32.7,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": 10.2,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": 75.8,
          "benchmark_llmstats_swe_bench_pro": 57.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 70.3,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 73.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 51.3,
          "benchmark_swe_bench_verified": 77.7
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "seed-2.0-pro",
          "source_name": "Seed 2.0 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.0 Pro",
          "family_id": "bytedance/seed-2-0-pro",
          "provider": "Bytedance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 39,
          "category_score": 21,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.5
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 16,
          "category_score": 36.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.5,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 71,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 83.8,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 59.8,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "coding",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 32.8,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 67.6,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 80.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": 57.8,
          "benchmark_swe_bench_verified": null
        }
      ],
      "long_context": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 21.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 26.6,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 34,
          "category_score": 10.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 19,
          "category_score": 22.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-sonnet-4-5-20250929",
          "source_name": "Claude Sonnet 4.5",
          "original_source_name": "5Claude Sonnet 4.5",
          "canonical_name": "Claude Sonnet 4.5",
          "family_id": "unknown/claude-sonnet-4-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 26,
          "category_score": 19,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-5-20250929",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": 47.5,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 31,
          "category_score": 13.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 37,
          "category_score": 3.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 35,
          "category_score": 9.7,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gemini-2.5-pro",
          "source_name": "Gemini 2.5 Pro",
          "original_source_name": "29Gemini 2.5 Pro",
          "canonical_name": "Gemini 2.5 Pro",
          "family_id": "google/gemini-2-5-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 18.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-2.5-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gemini-3-flash-preview",
          "source_name": "Gemini 3 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Flash",
          "family_id": "google/gemini-3-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 36,
          "category_score": 9.2,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gemini-3-pro-preview",
          "source_name": "Gemini 3 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Pro",
          "family_id": "google/gemini-3-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 32,
          "category_score": 11.9,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 32,
          "category_score": 11.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gemini-3.6-flash",
          "source_name": "Gemini 3.6 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.6 Flash",
          "family_id": "google/gemini-3-6-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 23,
          "category_score": 21.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.6-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5-2025-08-07",
          "source_name": "GPT-5",
          "original_source_name": "10GPT-5",
          "canonical_name": "GPT-5",
          "family_id": "unknown/gpt-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 25,
          "category_score": 20.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5-2025-08-07",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 18.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": 91.9,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": 55.6,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": 22.8,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": 55.1,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": 29.8,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 17,
          "category_score": 22.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 16,
          "category_score": 23.5,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 1,
          "category_score": 35.2,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 3,
          "category_score": 28.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 9,
          "category_score": 26.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 73.4,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "kimi-k2.5",
          "source_name": "Kimi K2.5",
          "original_source_name": "29Kimi K2.5",
          "canonical_name": "Kimi K2.5",
          "family_id": "unknown/kimi-k2-5",
          "provider": "Moonshot AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 8,
          "category_score": 27.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 70,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 61,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 75.9,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "mai-thinking-1",
          "source_name": "MAI-Thinking-1",
          "original_source_name": "22MAI-Thinking-1",
          "canonical_name": "MAI-Thinking-1",
          "family_id": "unknown/mai-thinking-1",
          "provider": "Microsoft",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 21.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/mai-thinking-1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 61,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "minimax-m1-40k",
          "source_name": "MiniMax M1 40K",
          "original_source_name": "13MiniMax M1 40K",
          "canonical_name": "MiniMax M1 40K",
          "family_id": "unknown/minimax-m1-40k",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 25.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/minimax-m1-40k",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 61,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "minimax-m1-80k",
          "source_name": "MiniMax M1 80K",
          "original_source_name": "18MiniMax M1 80K",
          "canonical_name": "MiniMax M1 80K",
          "family_id": "unknown/minimax-m1-80k",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 18,
          "category_score": 22.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/minimax-m1-80k",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 61.5,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "mistral-small-latest",
          "source_name": "Mistral Small 4",
          "original_source_name": "12Mistral Small 4",
          "canonical_name": "Mistral Small 4",
          "family_id": "mistral-ai/mistral-small-4",
          "provider": "Mistral AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 12,
          "category_score": 25.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/mistral-small-latest",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 71.2,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "nemotron-3-ultra-550b-a55b",
          "source_name": "Nemotron 3 Ultra (550B A55B)",
          "original_source_name": "15Nemotron 3 Ultra (550B A55B)",
          "canonical_name": "Nemotron 3 Ultra (550B A55B)",
          "family_id": "unknown/nemotron-3-ultra-550b-a55b",
          "provider": "NVIDIA",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 24.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/nemotron-3-ultra-550b-a55b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 65.4,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 61.9,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.5-122b-a10b",
          "source_name": "Qwen3.5-122B-A10B",
          "original_source_name": "30Qwen3.5-122B-A10B",
          "canonical_name": "Qwen3.5-122B-A10B",
          "family_id": "unknown/qwen3-5-122b-a10b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 11,
          "category_score": 25.9,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-122b-a10b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 66.9,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 60.2,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 74.4,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.5-27b",
          "source_name": "Qwen3.5-27B",
          "original_source_name": "14Qwen3.5-27B",
          "canonical_name": "Qwen3.5-27B",
          "family_id": "unknown/qwen3-5-27b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 14,
          "category_score": 25.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-27b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 66.1,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 60.6,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 73.6,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.5-35b-a3b",
          "source_name": "Qwen3.5-35B-A3B",
          "original_source_name": "20Qwen3.5-35B-A3B",
          "canonical_name": "Qwen3.5-35B-A3B",
          "family_id": "unknown/qwen3-5-35b-a3b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 21.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-35b-a3b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 58.5,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 59,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 71.4,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 6,
          "category_score": 28.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 68.7,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 63.2,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.5-9b",
          "source_name": "Qwen3.5-9B",
          "original_source_name": "27Qwen3.5-9B",
          "canonical_name": "Qwen3.5-9B",
          "family_id": "unknown/qwen3-5-9b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 18.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-9b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 63,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 55.2,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.6-27b",
          "source_name": "Qwen3.6-27B",
          "original_source_name": "28Qwen3.6-27B",
          "canonical_name": "Qwen3.6-27B",
          "family_id": "unknown/qwen3-6-27b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 28,
          "category_score": 18.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-27b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.6-35b-a3b",
          "source_name": "Qwen3.6-35B-A3B",
          "original_source_name": "24Qwen3.6-35B-A3B",
          "canonical_name": "Qwen3.6-35B-A3B",
          "family_id": "unknown/qwen3-6-35b-a3b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 24,
          "category_score": 20.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-35b-a3b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 71.4,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 2,
          "category_score": 29.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": 68.3,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": 62,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "qwen3.7-plus",
          "source_name": "Qwen3.7-Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.7-Plus",
          "family_id": "alibaba/qwen3-7-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 4,
          "category_score": 28.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 76.2,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 5,
          "category_score": 28.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 78,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "long_context",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 27.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": 76.8,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ],
      "math": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-fable-5",
          "source_name": "Claude Fable 5",
          "original_source_name": null,
          "canonical_name": "Claude Fable 5",
          "family_id": "anthropic/claude-fable-5",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 8,
          "category_score": 41.5,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/claude-fable-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 64.5,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 1,
          "category_score": 47.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 64.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 14,
          "category_score": 40.4,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": 99.8,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 53.1,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 19,
          "category_score": 39.5,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 54.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 18,
          "category_score": 39.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 57.9,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-opus-5",
          "source_name": "Claude Opus 5",
          "original_source_name": null,
          "canonical_name": "Claude Opus 5",
          "family_id": "anthropic/claude-opus-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 4,
          "category_score": 42.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-opus-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 64.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 34,
          "category_score": 34.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 15,
          "category_score": 40.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 45.1,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 86.2,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 9,
          "category_score": 41.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 48.2,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 87.5,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gemini-3-flash-preview",
          "source_name": "Gemini 3 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Flash",
          "family_id": "google/gemini-3-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 28,
          "category_score": 37.3,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
          "benchmark_aime_2025": 99.7,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 43.5,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gemini-3-pro-preview",
          "source_name": "Gemini 3 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Pro",
          "family_id": "google/gemini-3-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 37.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 45.8,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 3,
          "category_score": 43,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 51.4,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "glm-5.2",
          "source_name": "GLM-5.2",
          "original_source_name": null,
          "canonical_name": "GLM-5.2",
          "family_id": "zai/glm-5-2",
          "provider": "ZAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 6,
          "category_score": 41.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-5.2",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 54.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 37,
          "category_score": 30,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": 94,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 23,
          "category_score": 38.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.2-pro-2025-12-11",
          "source_name": "GPT-5.2 Pro",
          "original_source_name": null,
          "canonical_name": "GPT-5.2 Pro",
          "family_id": "openai/gpt-5-2-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 39.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-pro-2025-12-11",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 36.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 38.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 52.2,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.5-pro",
          "source_name": "GPT-5.5 Pro",
          "original_source_name": "25GPT-5.5 Pro",
          "canonical_name": "GPT-5.5 Pro",
          "family_id": "unknown/gpt-5-5-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 25,
          "category_score": 37.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 57.2,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 38,
          "category_score": 29.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 32,
          "category_score": 36.8,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 35,
          "category_score": 33.4,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "grok-4-heavy",
          "source_name": "Grok-4 Heavy",
          "original_source_name": null,
          "canonical_name": "Grok-4 Heavy",
          "family_id": "xai/grok-4-heavy",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 41.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4-heavy",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 50.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 33,
          "category_score": 35.7,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "kimi-k2-thinking-0905",
          "source_name": "Kimi K2-Thinking-0905",
          "original_source_name": "21Kimi K2-Thinking-0905",
          "canonical_name": "Kimi K2-Thinking-0905",
          "family_id": "unknown/kimi-k2-thinking-0905",
          "provider": "Moonshot AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 38.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2-thinking-0905",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 51,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 84.6,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "kimi-k2.5",
          "source_name": "Kimi K2.5",
          "original_source_name": "29Kimi K2.5",
          "canonical_name": "Kimi K2.5",
          "family_id": "unknown/kimi-k2-5",
          "provider": "Moonshot AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 37.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.5",
          "benchmark_aime_2025": 96.1,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 50.2,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 87.1,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "kimi-k2.6",
          "source_name": "Kimi K2.6",
          "original_source_name": null,
          "canonical_name": "Kimi K2.6",
          "family_id": "moonshot-ai/kimi-k2-6",
          "provider": "MoonshotAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 24,
          "category_score": 37.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "kimi-k3",
          "source_name": "Kimi K3",
          "original_source_name": null,
          "canonical_name": "Kimi K3",
          "family_id": "kimi/kimi-k3",
          "provider": "MoonshotAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 5,
          "category_score": 42,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/kimi-k3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 56,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 17,
          "category_score": 40,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 58.4,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "muse-spark-1.1",
          "source_name": "Muse Spark 1.1",
          "original_source_name": null,
          "canonical_name": "Muse Spark 1.1",
          "family_id": "unknown/muse-spark-1-1",
          "provider": "Baidu",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 11,
          "category_score": 40.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 62.1,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "qwen3.5-122b-a10b",
          "source_name": "Qwen3.5-122B-A10B",
          "original_source_name": "30Qwen3.5-122B-A10B",
          "canonical_name": "Qwen3.5-122B-A10B",
          "family_id": "unknown/qwen3-5-122b-a10b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 36.9,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-122b-a10b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 47.5,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 86.7,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 26,
          "category_score": 37.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 87.8,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 16,
          "category_score": 40.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 88.5,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "qwen3.7-max",
          "source_name": "Qwen3.7 Max",
          "original_source_name": null,
          "canonical_name": "Qwen3.7 Max",
          "family_id": "alibaba/qwen3-7",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 2,
          "category_score": 44,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 41.4,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 89.6,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "qwen3.7-plus",
          "source_name": "Qwen3.7-Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.7-Plus",
          "family_id": "alibaba/qwen3-7-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 12,
          "category_score": 40.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": 88.5,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "seed-2.0-pro",
          "source_name": "Seed 2.0 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.0 Pro",
          "family_id": "bytedance/seed-2-0-pro",
          "provider": "Bytedance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 36,
          "category_score": 32.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
          "benchmark_aime_2025": 98.3,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 40.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 55.7,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": 90.7,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "math",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 40.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": 54.6,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": 90.5,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ],
      "reasoning": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-fable-5",
          "source_name": "Claude Fable 5",
          "original_source_name": null,
          "canonical_name": "Claude Fable 5",
          "family_id": "anthropic/claude-fable-5",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 4,
          "category_score": 55.3,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/claude-fable-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 60.5,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 80,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 95
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 3,
          "category_score": 56.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 77.8,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 93.9
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 46.7,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": 99.8,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 53.5,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.8
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 14,
          "category_score": 47.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 51.4,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.3,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 87.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 7,
          "category_score": 52.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 54.6,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 69.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 88.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-opus-5",
          "source_name": "Claude Opus 5",
          "original_source_name": null,
          "canonical_name": "Claude Opus 5",
          "family_id": "anthropic/claude-opus-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 2,
          "category_score": 57.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-opus-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 62,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 36,
          "category_score": 39.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 79.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "claude-sonnet-5",
          "source_name": "Claude Sonnet 5",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 5",
          "family_id": "anthropic/claude-sonnet-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 9,
          "category_score": 50.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 53.9,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 63.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 85.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 33,
          "category_score": 40.5,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 52.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 79
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 23,
          "category_score": 44.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 44.4,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 55.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gemini-3-flash-preview",
          "source_name": "Gemini 3 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Flash",
          "family_id": "google/gemini-3-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 39,
          "category_score": 38.5,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
          "benchmark_aime_2025": 99.7,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gemini-3-pro-preview",
          "source_name": "Gemini 3 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Pro",
          "family_id": "google/gemini-3-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 38,
          "category_score": 39.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 21,
          "category_score": 45.1,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 54.2,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.6
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gemini-3.5-flash",
          "source_name": "Gemini 3.5 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.5 Flash",
          "family_id": "google/gemini-3-5-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 45.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.5-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 45.7,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gemini-3.6-flash",
          "source_name": "Gemini 3.6 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.6 Flash",
          "family_id": "google/gemini-3-6-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 43.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.6-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 47.4,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "glm-5.2",
          "source_name": "GLM-5.2",
          "original_source_name": null,
          "canonical_name": "GLM-5.2",
          "family_id": "zai/glm-5-2",
          "provider": "ZAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 17,
          "category_score": 46.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-5.2",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 62.1,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 40,
          "category_score": 36.8,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": 94,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.3
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 41.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.2-pro-2025-12-11",
          "source_name": "GPT-5.2 Pro",
          "original_source_name": null,
          "canonical_name": "GPT-5.2 Pro",
          "family_id": "openai/gpt-5-2-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 41.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-pro-2025-12-11",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 24,
          "category_score": 44,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 47.6,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 48.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.5-pro",
          "source_name": "GPT-5.5 Pro",
          "original_source_name": "25GPT-5.5 Pro",
          "canonical_name": "GPT-5.5 Pro",
          "family_id": "unknown/gpt-5-5-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 19,
          "category_score": 45.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 16,
          "category_score": 46.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 53.1,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 62.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 1,
          "category_score": 58.1,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 58.3,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 8,
          "category_score": 52.1,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 53.1,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 63.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "grok-4-heavy",
          "source_name": "Grok-4 Heavy",
          "original_source_name": null,
          "canonical_name": "Grok-4 Heavy",
          "family_id": "xai/grok-4-heavy",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 35,
          "category_score": 39.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4-heavy",
          "benchmark_aime_2025": 100,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "grok-4.5",
          "source_name": "Grok 4.5",
          "original_source_name": null,
          "canonical_name": "Grok 4.5",
          "family_id": "xai/grok-4-5",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 11,
          "category_score": 48.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 51.4,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 64.7,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 25,
          "category_score": 43.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.9,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "kimi-k2.6",
          "source_name": "Kimi K2.6",
          "original_source_name": null,
          "canonical_name": "Kimi K2.6",
          "family_id": "moonshot-ai/kimi-k2-6",
          "provider": "MoonshotAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 44.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 40.1,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": 89.6,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 58.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.2
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "kimi-k3",
          "source_name": "Kimi K3",
          "original_source_name": null,
          "canonical_name": "Kimi K3",
          "family_id": "kimi/kimi-k3",
          "provider": "MoonshotAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 5,
          "category_score": 54.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/kimi-k3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 55.6,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "minimax-m3",
          "source_name": "MiniMax M3",
          "original_source_name": null,
          "canonical_name": "MiniMax M3",
          "family_id": "minimax/minimax-m3",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 28,
          "category_score": 43.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/minimax-m3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 47.7,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 59,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.5
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 31,
          "category_score": 41.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 52.4,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 77.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "muse-spark-1.1",
          "source_name": "Muse Spark 1.1",
          "original_source_name": null,
          "canonical_name": "Muse Spark 1.1",
          "family_id": "unknown/muse-spark-1-1",
          "provider": "Baidu",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 6,
          "category_score": 52.3,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 61.5,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 36,
          "category_score": 39.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 32,
          "category_score": 41.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 56.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 78.8
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "qwen3.7-max",
          "source_name": "Qwen3.7 Max",
          "original_source_name": null,
          "canonical_name": "Qwen3.7 Max",
          "family_id": "alibaba/qwen3-7",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 13,
          "category_score": 47.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": 43.6,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": 91.6,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 60.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 80.4
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "qwen3.7-plus",
          "source_name": "Qwen3.7-Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.7-Plus",
          "family_id": "alibaba/qwen3-7-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 26,
          "category_score": 43.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": 89.6,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.6,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 77.7
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "seed-2.0-pro",
          "source_name": "Seed 2.0 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.0 Pro",
          "family_id": "bytedance/seed-2-0-pro",
          "provider": "Bytedance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 34,
          "category_score": 39.8,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
          "benchmark_aime_2025": 98.3,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": 76.5
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 12,
          "category_score": 48.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57.5,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "reasoning",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 18,
          "category_score": 45.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": 57,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ],
      "research": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 8,
          "category_score": 26.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 86.9,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 24.6,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 91.3,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 24,
          "category_score": 17.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 79.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 6,
          "category_score": 26.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 93.1,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-opus-5",
          "source_name": "Claude Opus 5",
          "original_source_name": null,
          "canonical_name": "Claude Opus 5",
          "family_id": "anthropic/claude-opus-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 2,
          "category_score": 30.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-opus-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 90.8,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 32,
          "category_score": 14.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 74.7,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "claude-sonnet-5",
          "source_name": "Claude Sonnet 5",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 5",
          "family_id": "anthropic/claude-sonnet-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 14,
          "category_score": 22.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84.7,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 33,
          "category_score": 13.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 73.2,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 18,
          "category_score": 19,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 83.4,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 12,
          "category_score": 23.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 85.9,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gemma-2-27b-it",
          "source_name": "Gemma 2 27B",
          "original_source_name": "26Gemma 2 27B",
          "canonical_name": "Gemma 2 27B",
          "family_id": "unknown/gemma-2-27b",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 26,
          "category_score": 16.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemma-2-27b-it",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": 34.5,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "glm-5.1",
          "source_name": "GLM-5.1",
          "original_source_name": null,
          "canonical_name": "GLM-5.1",
          "family_id": "unknown/glm-5-1",
          "provider": "Z AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 23,
          "category_score": 17.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/glm-5.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 79.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 34,
          "category_score": 8.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 31,
          "category_score": 15.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 65.8,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.2-pro-2025-12-11",
          "source_name": "GPT-5.2 Pro",
          "original_source_name": null,
          "canonical_name": "GPT-5.2 Pro",
          "family_id": "openai/gpt-5-2-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 25,
          "category_score": 16.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-pro-2025-12-11",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 77.9,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 17.8,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 82.7,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 16,
          "category_score": 21.9,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84.4,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.5-pro",
          "source_name": "GPT-5.5 Pro",
          "original_source_name": "25GPT-5.5 Pro",
          "canonical_name": "GPT-5.5 Pro",
          "family_id": "unknown/gpt-5-5-pro",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 4,
          "category_score": 27.9,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 90.1,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 20,
          "category_score": 18.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 83.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 3,
          "category_score": 28.9,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 90.4,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 5,
          "category_score": 27,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 87.5,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 9,
          "category_score": 24.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84.2,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 91,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 76.4,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "kimi-k2.5",
          "source_name": "Kimi K2.5",
          "original_source_name": "29Kimi K2.5",
          "canonical_name": "Kimi K2.5",
          "family_id": "unknown/kimi-k2-5",
          "provider": "Moonshot AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 22.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 74.9,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 77.1,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": 57.4,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 79,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "kimi-k2.6",
          "source_name": "Kimi K2.6",
          "original_source_name": null,
          "canonical_name": "Kimi K2.6",
          "family_id": "moonshot-ai/kimi-k2-6",
          "provider": "MoonshotAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 26.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 86.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 83,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 80.8,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "kimi-k3",
          "source_name": "Kimi K3",
          "original_source_name": null,
          "canonical_name": "Kimi K3",
          "family_id": "kimi/kimi-k3",
          "provider": "MoonshotAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 1,
          "category_score": 34.4,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/kimi-k3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 91.2,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 95,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "mimo-v2-pro",
          "source_name": "MiMo-V2-Pro",
          "original_source_name": "23MiMo-V2-Pro",
          "canonical_name": "MiMo-V2-Pro",
          "family_id": "unknown/mimo-v2-pro",
          "provider": "Xiaomi",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 17.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/mimo-v2-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": 86.7,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "minimax-m2.5",
          "source_name": "MiniMax M2.5",
          "original_source_name": "29MiniMax M2.5",
          "canonical_name": "MiniMax M2.5",
          "family_id": "unknown/minimax-m2-5",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 15.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/minimax-m2.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 76.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "minimax-m3",
          "source_name": "MiniMax M3",
          "original_source_name": null,
          "canonical_name": "MiniMax M3",
          "family_id": "minimax/minimax-m3",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 17,
          "category_score": 19.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/minimax-m3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 83.5,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 35,
          "category_score": 0.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "qwen3.5-122b-a10b",
          "source_name": "Qwen3.5-122B-A10B",
          "original_source_name": "30Qwen3.5-122B-A10B",
          "canonical_name": "Qwen3.5-122B-A10B",
          "family_id": "unknown/qwen3-5-122b-a10b",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 28,
          "category_score": 16.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-122b-a10b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": 69.9,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": 44.1,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 60.5,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 19,
          "category_score": 18.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 69,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": 70.3,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": 46.9,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 74,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 30,
          "category_score": 15.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": 74.3,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "seed-2.0-pro",
          "source_name": "Seed 2.0 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.0 Pro",
          "family_id": "bytedance/seed-2-0-pro",
          "provider": "Bytedance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 16.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 77.3,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 11,
          "category_score": 24.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 86.2,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "research",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 23.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": 84.9,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ],
      "tool_calling": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-fable-5",
          "source_name": "Claude Fable 5",
          "original_source_name": null,
          "canonical_name": "Claude Fable 5",
          "family_id": "anthropic/claude-fable-5",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 14,
          "category_score": 28.4,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/claude-fable-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 84.3,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-mythos-preview",
          "source_name": "Claude Mythos Preview",
          "original_source_name": null,
          "canonical_name": "Claude Mythos Preview",
          "family_id": "anthropic/claude-mythos-preview",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 9,
          "category_score": 29.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 82,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 26.6,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 91.9,
          "benchmark_llmstats_tau2_telecom": 99.3,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 65.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 62.7,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-opus-4-7",
          "source_name": "Claude Opus 4.7",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.7",
          "family_id": "anthropic/claude-opus-4-7",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 16,
          "category_score": 27.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 69.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 77.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-opus-4-8",
          "source_name": "Claude Opus 4.8",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.8",
          "family_id": "anthropic/claude-opus-4-8",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 5,
          "category_score": 33.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 74.6,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 59.9,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 82.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-opus-5",
          "source_name": "Claude Opus 5",
          "original_source_name": null,
          "canonical_name": "Claude Opus 5",
          "family_id": "anthropic/claude-opus-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 27.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-opus-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-sonnet-4-5-20250929",
          "source_name": "Claude Sonnet 4.5",
          "original_source_name": "5Claude Sonnet 4.5",
          "canonical_name": "Claude Sonnet 4.5",
          "family_id": "unknown/claude-sonnet-4-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 26.3,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-5-20250929",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 70,
          "benchmark_llmstats_tau_bench_retail": 86.2,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 33,
          "category_score": 22.9,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 91.7,
          "benchmark_llmstats_tau2_telecom": 97.9,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 61.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "claude-sonnet-5",
          "source_name": "Claude Sonnet 5",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 5",
          "family_id": "anthropic/claude-sonnet-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 28.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 80.4,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 54.3,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "deepseek-v4-flash-max",
          "source_name": "DeepSeek-V4-Flash-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Flash-Max",
          "family_id": "deepseek/deepseek-v4-flash",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 36,
          "category_score": 19.5,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 47.8,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 69,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "deepseek-v4-pro-max",
          "source_name": "DeepSeek-V4-Pro-Max",
          "original_source_name": null,
          "canonical_name": "DeepSeek-V4-Pro-Max",
          "family_id": "deepseek/deepseek-v4-pro",
          "provider": "DeepSeek",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 25,
          "category_score": 25.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 67.9,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 51.8,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 73.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gemini-3-flash-preview",
          "source_name": "Gemini 3 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Flash",
          "family_id": "google/gemini-3-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 38,
          "category_score": 18.4,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 49.4,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 57.4,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gemini-3-pro-preview",
          "source_name": "Gemini 3 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3 Pro",
          "family_id": "google/gemini-3-pro",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 41,
          "category_score": 13.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gemini-3.1-pro-preview",
          "source_name": "Gemini 3.1 Pro",
          "original_source_name": null,
          "canonical_name": "Gemini 3.1 Pro",
          "family_id": "google/gemini-3-1-pro-preview",
          "provider": "Google",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 28,
          "category_score": 24.8,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": 99.3,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 68.5,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 69.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gemini-3.5-flash",
          "source_name": "Gemini 3.5 Flash",
          "original_source_name": null,
          "canonical_name": "Gemini 3.5 Flash",
          "family_id": "google/gemini-3-5-flash",
          "provider": "Google",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 6,
          "category_score": 33.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gemini-3.5-flash",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 76.2,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 56.5,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 83.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "glm-5.2",
          "source_name": "GLM-5.2",
          "original_source_name": null,
          "canonical_name": "GLM-5.2",
          "family_id": "zai/glm-5-2",
          "provider": "ZAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 23,
          "category_score": 26.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-5.2",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 82.7,
          "benchmark_llmstats_toolathlon": 48.2,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76.8,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 37,
          "category_score": 19,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 67,
          "benchmark_llmstats_tau2_retail": 77.9,
          "benchmark_llmstats_tau2_telecom": 95.6,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 35,
          "category_score": 21.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 82,
          "benchmark_llmstats_tau2_telecom": 98.7,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 46.3,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 60.6,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.3-codex",
          "source_name": "GPT-5.3 Codex",
          "original_source_name": "20GPT-5.3 Codex",
          "canonical_name": "GPT-5.3 Codex",
          "family_id": "unknown/gpt-5-3-codex",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 26.8,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.3-codex",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 77.3,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 29,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": 98.9,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 75.1,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 54.6,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 67.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 31.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": 98,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 82.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 55.6,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 75.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.6-luna",
          "source_name": "GPT-5.6 Luna",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Luna",
          "family_id": "openai/gpt-5-6-luna",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 11,
          "category_score": 28.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 84.7,
          "benchmark_llmstats_toolathlon": 53.4,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.6-sol",
          "source_name": "GPT-5.6 Sol",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Sol",
          "family_id": "openai/gpt-5-6-sol",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 2,
          "category_score": 36.1,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 88.8,
          "benchmark_llmstats_toolathlon": 58,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "gpt-5.6-terra",
          "source_name": "GPT-5.6 Terra",
          "original_source_name": null,
          "canonical_name": "GPT-5.6 Terra",
          "family_id": "openai/gpt-5-6-terra",
          "provider": "OpenAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 4,
          "category_score": 34,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 87.4,
          "benchmark_llmstats_toolathlon": 53.1,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "grok-4.5",
          "source_name": "Grok 4.5",
          "original_source_name": null,
          "canonical_name": "Grok 4.5",
          "family_id": "xai/grok-4-5",
          "provider": "xAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 32,
          "category_score": 23,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/grok-4.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 83.3,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "hy3",
          "source_name": "Hy3",
          "original_source_name": null,
          "canonical_name": "Hy3",
          "family_id": "tencent/hy3",
          "provider": "Tencent",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 24,
          "category_score": 25.6,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/hy3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 71.7,
          "benchmark_llmstats_toolathlon": 48.5,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 79.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "kimi-k2.6",
          "source_name": "Kimi K2.6",
          "original_source_name": null,
          "canonical_name": "Kimi K2.6",
          "family_id": "moonshot-ai/kimi-k2-6",
          "provider": "MoonshotAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 31,
          "category_score": 23.5,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 66.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 50,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "kimi-k2.7-code",
          "source_name": "Kimi K2.7 Code",
          "original_source_name": null,
          "canonical_name": "Kimi K2.7 Code",
          "family_id": "kimi/kimi-k2-7-code",
          "provider": "Kimi",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 18,
          "category_score": 27.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/kimi-k2.7-code",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "kimi-k3",
          "source_name": "Kimi K3",
          "original_source_name": null,
          "canonical_name": "Kimi K3",
          "family_id": "kimi/kimi-k3",
          "provider": "MoonshotAI",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 1,
          "category_score": 39.2,
          "match_status": "matched_manual",
          "source_model_url": "https://llm-stats.com/models/kimi-k3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 88.3,
          "benchmark_llmstats_toolathlon": 73.2,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 84.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "llama-3.1-405b-instruct",
          "source_name": "Llama 3.1 405B Instruct",
          "original_source_name": "8Llama 3.1 405B Instruct",
          "canonical_name": "Llama 3.1 405B Instruct",
          "family_id": "unknown/llama-3-1-405b-instruct",
          "provider": "Meta",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 8,
          "category_score": 30.8,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/llama-3.1-405b-instruct",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "llama-3.1-70b-instruct",
          "source_name": "Llama 3.1 70B Instruct",
          "original_source_name": "29Llama 3.1 70B Instruct",
          "canonical_name": "Llama 3.1 70B Instruct",
          "family_id": "unknown/llama-3-1-70b-instruct",
          "provider": "Meta",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 24.5,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/llama-3.1-70b-instruct",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "longcat-flash-thinking-2601",
          "source_name": "LongCat-Flash-Thinking-2601",
          "original_source_name": "2LongCat-Flash-Thinking-2601",
          "canonical_name": "LongCat-Flash-Thinking-2601",
          "family_id": "unknown/longcat-flash-thinking-2601",
          "provider": "Meituan",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 17,
          "category_score": 27.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/longcat-flash-thinking-2601",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 76.5,
          "benchmark_llmstats_tau2_retail": 88.6,
          "benchmark_llmstats_tau2_telecom": 99.3,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "minimax-m3",
          "source_name": "MiniMax M3",
          "original_source_name": null,
          "canonical_name": "MiniMax M3",
          "family_id": "minimax/minimax-m3",
          "provider": "MiniMax",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 30,
          "category_score": 23.7,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/minimax-m3",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 66,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 74.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 40,
          "category_score": 16.8,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "muse-spark-1.1",
          "source_name": "Muse Spark 1.1",
          "original_source_name": null,
          "canonical_name": "Muse Spark 1.1",
          "family_id": "unknown/muse-spark-1-1",
          "provider": "Baidu",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 3,
          "category_score": 34.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 80,
          "benchmark_llmstats_toolathlon": 75.6,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 88.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 39,
          "category_score": 18.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 38.3,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "qwen3.6-plus",
          "source_name": "Qwen3.6 Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.6 Plus",
          "family_id": "alibaba/qwen3-6-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 34,
          "category_score": 22.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": 39.8,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 74.1,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "qwen3.7-max",
          "source_name": "Qwen3.7 Max",
          "original_source_name": null,
          "canonical_name": "Qwen3.7 Max",
          "family_id": "alibaba/qwen3-7",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 12,
          "category_score": 28.7,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-max",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 69.7,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 76.4,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "qwen3.7-plus",
          "source_name": "Qwen3.7-Plus",
          "original_source_name": null,
          "canonical_name": "Qwen3.7-Plus",
          "family_id": "alibaba/qwen3-7-plus",
          "provider": "Qwen",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 26,
          "category_score": 25.2,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": 70.3,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 73.2,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "seed-2.1-pro",
          "source_name": "Seed 2.1 Pro",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Pro",
          "family_id": "unknown/seed-2-1-pro",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 19,
          "category_score": 26.9,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 71,
          "benchmark_llmstats_toolathlon": 50.6,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 83.8,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "tool_calling",
          "source_model_id": "seed-2.1-turbo",
          "source_name": "Seed 2.1 Turbo",
          "original_source_name": null,
          "canonical_name": "Seed 2.1 Turbo",
          "family_id": "unknown/seed-2-1-turbo",
          "provider": "ByteDance",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 25,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": 67.6,
          "benchmark_llmstats_toolathlon": 49.1,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": 80.3,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ],
      "writing": [
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-3-7-sonnet-20250219",
          "source_name": "Claude 3.7 Sonnet",
          "original_source_name": "25Claude 3.7 Sonnet",
          "canonical_name": "Claude 3.7 Sonnet",
          "family_id": "unknown/claude-3-7-sonnet",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 25,
          "category_score": 18.6,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/claude-3-7-sonnet-20250219",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 58.4,
          "benchmark_llmstats_tau_bench_retail": 81.2,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-haiku-4-5-20251001",
          "source_name": "Claude Haiku 4.5",
          "original_source_name": "17Claude Haiku 4.5",
          "canonical_name": "Claude Haiku 4.5",
          "family_id": "unknown/claude-haiku-4-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 17,
          "category_score": 20.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/claude-haiku-4-5-20251001",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 63.6,
          "benchmark_llmstats_tau2_retail": 83.2,
          "benchmark_llmstats_tau2_telecom": 83,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-opus-4-1-20250805",
          "source_name": "Claude Opus 4.1",
          "original_source_name": "24Claude Opus 4.1",
          "canonical_name": "Claude Opus 4.1",
          "family_id": "unknown/claude-opus-4-1",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 24,
          "category_score": 19,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-1-20250805",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 56,
          "benchmark_llmstats_tau_bench_retail": 82.4,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-opus-4-20250514",
          "source_name": "Claude Opus 4",
          "original_source_name": "18Claude Opus 4",
          "canonical_name": "Claude Opus 4",
          "family_id": "unknown/claude-opus-4",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 18,
          "category_score": 19.9,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-20250514",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 59.6,
          "benchmark_llmstats_tau_bench_retail": 81.4,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-opus-4-5-20251101",
          "source_name": "Claude Opus 4.5",
          "original_source_name": "3Claude Opus 4.5",
          "canonical_name": "Claude Opus 4.5",
          "family_id": "unknown/claude-opus-4-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 3,
          "category_score": 27.2,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-5-20251101",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 88.9,
          "benchmark_llmstats_tau2_telecom": 98.2,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-opus-4-6",
          "source_name": "Claude Opus 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Opus 4.6",
          "family_id": "anthropic/claude-opus-4-6",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 1,
          "category_score": 31.9,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 91.9,
          "benchmark_llmstats_tau2_telecom": 99.3,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-sonnet-4-20250514",
          "source_name": "Claude Sonnet 4",
          "original_source_name": "21Claude Sonnet 4",
          "canonical_name": "Claude Sonnet 4",
          "family_id": "unknown/claude-sonnet-4",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 21,
          "category_score": 19.2,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-20250514",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 60,
          "benchmark_llmstats_tau_bench_retail": 80.5,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-sonnet-4-5-20250929",
          "source_name": "Claude Sonnet 4.5",
          "original_source_name": "5Claude Sonnet 4.5",
          "canonical_name": "Claude Sonnet 4.5",
          "family_id": "unknown/claude-sonnet-4-5",
          "provider": "Anthropic",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 5,
          "category_score": 26.5,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-5-20250929",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 70,
          "benchmark_llmstats_tau_bench_retail": 86.2,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "claude-sonnet-4-6",
          "source_name": "Claude Sonnet 4.6",
          "original_source_name": null,
          "canonical_name": "Claude Sonnet 4.6",
          "family_id": "anthropic/claude-sonnet-4-6",
          "provider": "Anthropic",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 4,
          "category_score": 27.1,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 91.7,
          "benchmark_llmstats_tau2_telecom": 97.9,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "glm-4.5",
          "source_name": "GLM-4.5",
          "original_source_name": "20GLM-4.5",
          "canonical_name": "GLM-4.5",
          "family_id": "unknown/glm-4-5",
          "provider": "Z AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 20,
          "category_score": 19.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-4.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 60.4,
          "benchmark_llmstats_tau_bench_retail": 79.7,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "glm-4.5-air",
          "source_name": "GLM-4.5-Air",
          "original_source_name": "19GLM-4.5-Air",
          "canonical_name": "GLM-4.5-Air",
          "family_id": "unknown/glm-4-5-air",
          "provider": "Z AI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 19,
          "category_score": 19.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/glm-4.5-air",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 60.8,
          "benchmark_llmstats_tau_bench_retail": 77.9,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5-2025-08-07",
          "source_name": "GPT-5",
          "original_source_name": "10GPT-5",
          "canonical_name": "GPT-5",
          "family_id": "unknown/gpt-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 10,
          "category_score": 22.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5-2025-08-07",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 69.6,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 62.6,
          "benchmark_llmstats_tau2_retail": 81.1,
          "benchmark_llmstats_tau2_telecom": 96.7,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.1-2025-11-13",
          "source_name": "GPT-5.1",
          "original_source_name": null,
          "canonical_name": "GPT-5.1",
          "family_id": "openai/gpt-5-1",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 13,
          "category_score": 21.6,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 67,
          "benchmark_llmstats_tau2_retail": 77.9,
          "benchmark_llmstats_tau2_telecom": 95.6,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.1-instant-2025-11-12",
          "source_name": "GPT-5.1 Instant",
          "original_source_name": "12GPT-5.1 Instant",
          "canonical_name": "GPT-5.1 Instant",
          "family_id": "unknown/gpt-5-1-instant",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 12,
          "category_score": 21.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-instant-2025-11-12",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 67,
          "benchmark_llmstats_tau2_retail": 77.9,
          "benchmark_llmstats_tau2_telecom": 95.6,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.1-thinking-2025-11-12",
          "source_name": "GPT-5.1 Thinking",
          "original_source_name": "11GPT-5.1 Thinking",
          "canonical_name": "GPT-5.1 Thinking",
          "family_id": "unknown/gpt-5-1-thinking",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 11,
          "category_score": 21.7,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.1-thinking-2025-11-12",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 67,
          "benchmark_llmstats_tau2_retail": 77.9,
          "benchmark_llmstats_tau2_telecom": 95.6,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.2-2025-12-11",
          "source_name": "GPT-5.2",
          "original_source_name": null,
          "canonical_name": "GPT-5.2",
          "family_id": "openai/gpt-5-2",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 6,
          "category_score": 25.3,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": 82,
          "benchmark_llmstats_tau2_telecom": 98.7,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.4",
          "source_name": "GPT-5.4",
          "original_source_name": null,
          "canonical_name": "GPT-5.4",
          "family_id": "openai/gpt-5-4",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 7,
          "category_score": 24.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/gpt-5.4",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": 98.9,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "gpt-5.5",
          "source_name": "GPT-5.5",
          "original_source_name": null,
          "canonical_name": "GPT-5.5",
          "family_id": "openai/gpt-5-5",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 15,
          "category_score": 21,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/gpt-5.5",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": 98,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "hermes-3-70b",
          "source_name": "Hermes 3 70B",
          "original_source_name": "14Hermes 3 70B",
          "canonical_name": "Hermes 3 70B",
          "family_id": "unknown/hermes-3-70b",
          "provider": "Nous Research",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 14,
          "category_score": 21.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/hermes-3-70b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": 89.9,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "longcat-flash-thinking",
          "source_name": "LongCat-Flash-Thinking",
          "original_source_name": "26LongCat-Flash-Thinking",
          "canonical_name": "LongCat-Flash-Thinking",
          "family_id": "unknown/longcat-flash-thinking",
          "provider": "Meituan",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 26,
          "category_score": 18.1,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/longcat-flash-thinking",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 67.5,
          "benchmark_llmstats_tau2_retail": 71.5,
          "benchmark_llmstats_tau2_telecom": 83.1,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "longcat-flash-thinking-2601",
          "source_name": "LongCat-Flash-Thinking-2601",
          "original_source_name": "2LongCat-Flash-Thinking-2601",
          "canonical_name": "LongCat-Flash-Thinking-2601",
          "family_id": "unknown/longcat-flash-thinking-2601",
          "provider": "Meituan",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 2,
          "category_score": 30,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/longcat-flash-thinking-2601",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 76.5,
          "benchmark_llmstats_tau2_retail": 88.6,
          "benchmark_llmstats_tau2_telecom": 99.3,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "mimo-v2-pro",
          "source_name": "MiMo-V2-Pro",
          "original_source_name": "23MiMo-V2-Pro",
          "canonical_name": "MiMo-V2-Pro",
          "family_id": "unknown/mimo-v2-pro",
          "provider": "Xiaomi",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 23,
          "category_score": 19.2,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/mimo-v2-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": 96.8,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "muse-spark",
          "source_name": "Muse Spark",
          "original_source_name": null,
          "canonical_name": "Muse Spark",
          "family_id": "meta/muse-spark",
          "provider": "Meta",
          "availability_class": "proprietary",
          "is_open_weights": false,
          "category_rank": 31,
          "category_score": 14.4,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/muse-spark",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "nova-2-lite",
          "source_name": "Nova 2 Lite",
          "original_source_name": "16Nova 2 Lite",
          "canonical_name": "Nova 2 Lite",
          "family_id": "unknown/nova-2-lite",
          "provider": "Amazon",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 16,
          "category_score": 20.4,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/nova-2-lite",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 76.6,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 64.8,
          "benchmark_llmstats_tau2_retail": 76.5,
          "benchmark_llmstats_tau2_telecom": 76,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "nova-2-omni",
          "source_name": "Nova 2 Omni",
          "original_source_name": "9Nova 2 Omni",
          "canonical_name": "Nova 2 Omni",
          "family_id": "unknown/nova-2-omni",
          "provider": "Amazon",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 9,
          "category_score": 23,
          "match_status": "identity_unresolved",
          "source_model_url": "https://llm-stats.com/models/nova-2-omni",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 75.5,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 68.8,
          "benchmark_llmstats_tau2_retail": 78.3,
          "benchmark_llmstats_tau2_telecom": 80,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "nova-2-pro",
          "source_name": "Nova 2 Pro",
          "original_source_name": "8Nova 2 Pro",
          "canonical_name": "Nova 2 Pro",
          "family_id": "unknown/nova-2-pro",
          "provider": "Amazon",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 8,
          "category_score": 23.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/nova-2-pro",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 77.7,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 65.2,
          "benchmark_llmstats_tau2_retail": 77.7,
          "benchmark_llmstats_tau2_telecom": 92.7,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "o3-2025-04-16",
          "source_name": "o3",
          "original_source_name": "27o3",
          "canonical_name": "o3",
          "family_id": "openai/o3",
          "provider": "OpenAI",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 27,
          "category_score": 18.1,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/o3-2025-04-16",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 60.4,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": 64.8,
          "benchmark_llmstats_tau2_retail": 80.2,
          "benchmark_llmstats_tau2_telecom": 58.2,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "qwen-2.5-72b-instruct",
          "source_name": "Qwen2.5 72B Instruct",
          "original_source_name": "22Qwen2.5 72B Instruct",
          "canonical_name": "Qwen2.5 72B Instruct",
          "family_id": "unknown/qwen2-5-72b-instruct",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 22,
          "category_score": 19.2,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/qwen-2.5-72b-instruct",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": 93.5,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "qwen3-coder-480b-a35b-instruct",
          "source_name": "Qwen3-Coder 480B A35B Instruct",
          "original_source_name": "29Qwen3-Coder 480B A35B Instruct",
          "canonical_name": "Qwen3-Coder 480B A35B Instruct",
          "family_id": "unknown/qwen3-coder-480b-a35b-instruct",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 29,
          "category_score": 17.4,
          "match_status": "source_missing",
          "source_model_url": "https://llm-stats.com/models/qwen3-coder-480b-a35b-instruct",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": 60,
          "benchmark_llmstats_tau_bench_retail": 77.5,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "qwen3-vl-235b-a22b-thinking",
          "source_name": "Qwen3 VL 235B A22B Thinking",
          "original_source_name": "28Qwen3 VL 235B A22B Thinking",
          "canonical_name": "Qwen3 VL 235B A22B Thinking",
          "family_id": "unknown/qwen3-vl-235b-a22b-thinking",
          "provider": "Alibaba",
          "availability_class": "unknown",
          "is_open_weights": null,
          "category_rank": 28,
          "category_score": 17.4,
          "match_status": "ambiguous",
          "source_model_url": "https://llm-stats.com/models/qwen3-vl-235b-a22b-thinking",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": 8.5,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": null,
          "benchmark_llmstats_multi_if": 79.1,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": 86.7,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        },
        {
          "schema_version": "powerbi-v2-wide",
          "snapshot_date": "2026-07-26",
          "source": "LLMStats",
          "capability": "writing",
          "source_model_id": "qwen3.5-397b-a17b",
          "source_name": "Qwen3.5-397B-A17B",
          "original_source_name": null,
          "canonical_name": "Qwen3.5-397B-A17B",
          "family_id": "alibaba/qwen3-5-397b-a17b",
          "provider": "Qwen",
          "availability_class": "open_weights",
          "is_open_weights": true,
          "category_rank": 30,
          "category_score": 17.3,
          "match_status": "matched_family",
          "source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
          "benchmark_aime_2025": null,
          "benchmark_arc_agi_v2": null,
          "benchmark_browsecomp": null,
          "benchmark_gpqa": null,
          "benchmark_llmstats_aa_lcr": null,
          "benchmark_llmstats_apex_agents": null,
          "benchmark_llmstats_browsecomp_zh": null,
          "benchmark_llmstats_charxiv_r": null,
          "benchmark_llmstats_deepsearchqa": null,
          "benchmark_llmstats_deepswe_1_1": null,
          "benchmark_llmstats_facts_grounding_default": null,
          "benchmark_llmstats_finance": null,
          "benchmark_llmstats_frontiercode_1_1": null,
          "benchmark_llmstats_frontiermath": null,
          "benchmark_llmstats_frontierswe": null,
          "benchmark_llmstats_gdpval_aa": null,
          "benchmark_llmstats_health": null,
          "benchmark_llmstats_hle": null,
          "benchmark_llmstats_humanity_s_last_exam": null,
          "benchmark_llmstats_legal": null,
          "benchmark_llmstats_livecodebench": null,
          "benchmark_llmstats_livecodebench_v6": null,
          "benchmark_llmstats_longbench_v2": null,
          "benchmark_llmstats_longbench_v2_short": null,
          "benchmark_llmstats_lvbench": null,
          "benchmark_llmstats_mathvista": null,
          "benchmark_llmstats_mm_mt_bench": null,
          "benchmark_llmstats_mmlu_pro": null,
          "benchmark_llmstats_mmmlu": null,
          "benchmark_llmstats_mmmu": null,
          "benchmark_llmstats_mmmu_pro": null,
          "benchmark_llmstats_mrcr_v2_8needle_32768_65536": null,
          "benchmark_llmstats_mrcr_v2_8needle_4096_8192": null,
          "benchmark_llmstats_mrcr_v2_8needle_upto_128k": null,
          "benchmark_llmstats_mt_bench": null,
          "benchmark_llmstats_multi_challenge": 67.6,
          "benchmark_llmstats_multi_if": null,
          "benchmark_llmstats_natural_questions": null,
          "benchmark_llmstats_osworld": null,
          "benchmark_llmstats_screenspot_pro": null,
          "benchmark_llmstats_seal_0": null,
          "benchmark_llmstats_simpleqa": null,
          "benchmark_llmstats_swe_bench_multilingual": null,
          "benchmark_llmstats_swe_bench_pro": null,
          "benchmark_llmstats_t2_bench": null,
          "benchmark_llmstats_tau2_airline": null,
          "benchmark_llmstats_tau2_retail": null,
          "benchmark_llmstats_tau2_telecom": null,
          "benchmark_llmstats_tau_bench_airline": null,
          "benchmark_llmstats_tau_bench_retail": null,
          "benchmark_llmstats_terminal_bench_2_0": null,
          "benchmark_llmstats_terminal_bench_2_1": null,
          "benchmark_llmstats_toolathlon": null,
          "benchmark_llmstats_vision": null,
          "benchmark_llmstats_widesearch": null,
          "benchmark_llmstats_writingbench": null,
          "benchmark_mcp_atlas": null,
          "benchmark_mrcr_v2": null,
          "benchmark_scicode": null,
          "benchmark_swe_bench_verified": null
        }
      ]
    }
  },
  "llmdex": {
    "families": [
      {
        "family_id": "openai/gpt-5-6-sol",
        "canonical_family_name": "GPT-5.6 Sol",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-6-sol:max",
        "aa_representative_name": "GPT-5.6 Sol (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 59,
        "aa_rank": 4,
        "aa_official_coding_index": 72,
        "llmstats_source_name": "GPT-5.6 Sol",
        "llmstats_source_model_id": "gpt-5.6-sol",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.6-sol",
        "llmstats_general_score": 58,
        "llmstats_general_rank": 1,
        "llmstats_coding_score": 50.1,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 5,
        "output_cost": 30,
        "tokens_per_second": 66,
        "latency": 144.56,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 100,
        "llmstats_percentile": 100,
        "llmdex_score": 100,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 1,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 100,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 90.625,
        "llmstats_coding_percentile": 100,
        "llmdex_coding_score": 95.3125,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 2,
        "is_sota": true,
        "is_open_sota": false
      },
      {
        "family_id": "kimi/kimi-k3",
        "canonical_family_name": "Kimi K3",
        "provider": "Kimi",
        "aa_representative_variant_id": "kimi/kimi-k3:default",
        "aa_representative_name": "Kimi K3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 57,
        "aa_rank": 7,
        "aa_official_coding_index": 72,
        "llmstats_source_name": "Kimi K3",
        "llmstats_source_model_id": "kimi-k3",
        "llmstats_source_model_url": "https://llm-stats.com/models/kimi-k3",
        "llmstats_general_score": 55.7,
        "llmstats_general_rank": 3,
        "llmstats_coding_score": 44.9,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 3,
        "output_cost": 15,
        "tokens_per_second": 32,
        "latency": 189.77,
        "context_window": 1050000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 93.33333333333333,
        "llmstats_percentile": 93.33333333333333,
        "llmdex_score": 93.33333333333333,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 2,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 100,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 90.625,
        "llmstats_coding_percentile": 81.25,
        "llmdex_coding_score": 85.9375,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 3,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-opus-4-8",
        "canonical_family_name": "Claude Opus 4.8",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-opus-4-8:max",
        "aa_representative_name": "Claude Opus 4.8 (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 56,
        "aa_rank": 10,
        "aa_official_coding_index": 69,
        "llmstats_source_name": "Claude Opus 4.8",
        "llmstats_source_model_id": "claude-opus-4-8",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-8",
        "llmstats_general_score": 52.6,
        "llmstats_general_rank": 5,
        "llmstats_coding_score": 43.9,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 5,
        "output_cost": 25,
        "tokens_per_second": 56,
        "latency": 29.5,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 86.66666666666667,
        "llmstats_percentile": 80,
        "llmdex_score": 83.33333333333334,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 3.5,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 93.33333333333333,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 75,
        "llmstats_coding_percentile": 75,
        "llmdex_coding_score": 75,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 5,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-6-terra",
        "canonical_family_name": "GPT-5.6 Terra",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-6-terra:max",
        "aa_representative_name": "GPT-5.6 Terra (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 55,
        "aa_rank": 11,
        "aa_official_coding_index": 71,
        "llmstats_source_name": "GPT-5.6 Terra",
        "llmstats_source_model_id": "gpt-5.6-terra",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.6-terra",
        "llmstats_general_score": 53.3,
        "llmstats_general_rank": 4,
        "llmstats_coding_score": 46,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2.5,
        "output_cost": 15,
        "tokens_per_second": 136,
        "latency": 178.38,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 80,
        "llmstats_percentile": 86.66666666666667,
        "llmdex_score": 83.33333333333334,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 3.5,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 93.33333333333333,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 81.25,
        "llmstats_coding_percentile": 87.5,
        "llmdex_coding_score": 84.375,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 4,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-6-luna",
        "canonical_family_name": "GPT-5.6 Luna",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-6-luna:max",
        "aa_representative_name": "GPT-5.6 Luna (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 51,
        "aa_rank": 16,
        "aa_official_coding_index": 67,
        "llmstats_source_name": "GPT-5.6 Luna",
        "llmstats_source_model_id": "gpt-5.6-luna",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.6-luna",
        "llmstats_general_score": 46.8,
        "llmstats_general_rank": 9,
        "llmstats_coding_score": 39.3,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1,
        "output_cost": 6,
        "tokens_per_second": 188,
        "latency": 139.35,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 73.33333333333333,
        "llmstats_percentile": 73.33333333333333,
        "llmdex_score": 73.33333333333333,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 5,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 100,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 68.75,
        "llmstats_coding_percentile": 68.75,
        "llmdex_coding_score": 68.75,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 6,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-7",
        "canonical_family_name": "Qwen3.7",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-7:max",
        "aa_representative_name": "Qwen3.7 Max",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 46,
        "aa_rank": 27,
        "aa_official_coding_index": 62,
        "llmstats_source_name": "Qwen3.7 Max",
        "llmstats_source_model_id": "qwen3.7-max",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.7-max",
        "llmstats_general_score": 46.7,
        "llmstats_general_rank": 10,
        "llmstats_coding_score": 38.9,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2.5,
        "output_cost": 7.5,
        "tokens_per_second": 197,
        "latency": 2.62,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 63.333333333333336,
        "llmstats_percentile": 66.66666666666667,
        "llmdex_score": 65,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 6,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 96.66666666666666,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 56.25,
        "llmstats_coding_percentile": 56.25,
        "llmdex_coding_score": 56.25,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 7,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "deepseek/deepseek-v4-pro",
        "canonical_family_name": "DeepSeek V4 Pro",
        "provider": "DeepSeek",
        "aa_representative_variant_id": "deepseek/deepseek-v4-pro:max",
        "aa_representative_name": "DeepSeek V4 Pro (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 44,
        "aa_rank": 31,
        "aa_official_coding_index": 57,
        "llmstats_source_name": "DeepSeek-V4-Pro-Max",
        "llmstats_source_model_id": "deepseek-v4-pro-max",
        "llmstats_source_model_url": "https://llm-stats.com/models/deepseek-v4-pro-max",
        "llmstats_general_score": 44,
        "llmstats_general_rank": 14,
        "llmstats_coding_score": 33.8,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.43,
        "output_cost": 0.87,
        "tokens_per_second": 67,
        "latency": 1.61,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 53.333333333333336,
        "llmstats_percentile": 53.333333333333336,
        "llmdex_score": 53.333333333333336,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 7,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 100,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 46.875,
        "llmstats_coding_percentile": 43.75,
        "llmdex_coding_score": 45.3125,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 9,
        "is_sota": false,
        "is_open_sota": true
      },
      {
        "family_id": "anthropic/claude-opus-4-7",
        "canonical_family_name": "Claude Opus 4.7",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-opus-4-7:high-non-reasoning",
        "aa_representative_name": "Claude Opus 4.7 (Non-reasoning, high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 43,
        "aa_rank": 36,
        "aa_official_coding_index": 50,
        "llmstats_source_name": "Claude Opus 4.7",
        "llmstats_source_model_id": "claude-opus-4-7",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-7",
        "llmstats_general_score": 45.6,
        "llmstats_general_rank": 12,
        "llmstats_coding_score": 39.2,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 5,
        "output_cost": 25,
        "tokens_per_second": 45,
        "latency": 1.59,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 43.333333333333336,
        "llmstats_percentile": 60,
        "llmdex_score": 51.66666666666667,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 8,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 83.33333333333334,
        "agreement_label": "Moderate agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 12.5,
        "llmstats_coding_percentile": 62.5,
        "llmdex_coding_score": 37.5,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 11,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-1-pro-preview",
        "canonical_family_name": "Gemini 3.1 Pro Preview",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-1-pro-preview:preview",
        "aa_representative_name": "Gemini 3.1 Pro Preview",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 46,
        "aa_rank": 25,
        "aa_official_coding_index": 66.5,
        "llmstats_source_name": "Gemini 3.1 Pro",
        "llmstats_source_model_id": "gemini-3.1-pro-preview",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-3.1-pro-preview",
        "llmstats_general_score": 43.6,
        "llmstats_general_rank": 18,
        "llmstats_coding_score": 33,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 12,
        "tokens_per_second": 124,
        "latency": 35.43,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 63.333333333333336,
        "llmstats_percentile": 33.333333333333336,
        "llmdex_score": 48.333333333333336,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 9,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 70,
        "agreement_label": "Low agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 62.5,
        "llmstats_coding_percentile": 37.5,
        "llmdex_coding_score": 50,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 8,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "tencent/hy3",
        "canonical_family_name": "Hy3",
        "provider": "Tencent",
        "aa_representative_variant_id": "tencent/hy3:default",
        "aa_representative_name": "Hy3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 41,
        "aa_rank": 40,
        "aa_official_coding_index": 56,
        "llmstats_source_name": "Hy3",
        "llmstats_source_model_id": "hy3",
        "llmstats_source_model_url": "https://llm-stats.com/models/hy3",
        "llmstats_general_score": 43.8,
        "llmstats_general_rank": 15.5,
        "llmstats_coding_score": 35.7,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.14,
        "output_cost": 0.58,
        "tokens_per_second": 62,
        "latency": 2.7,
        "context_window": 256000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 33.333333333333336,
        "llmstats_percentile": 43.333333333333336,
        "llmdex_score": 38.333333333333336,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 10,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 90,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 37.5,
        "llmstats_coding_percentile": 50,
        "llmdex_coding_score": 43.75,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 10,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/muse-spark",
        "canonical_family_name": "Muse Spark",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/muse-spark:default",
        "aa_representative_name": "Muse Spark",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 43,
        "aa_rank": 35,
        "aa_official_coding_index": 57,
        "llmstats_source_name": "Muse Spark",
        "llmstats_source_model_id": "muse-spark",
        "llmstats_source_model_url": "https://llm-stats.com/models/muse-spark",
        "llmstats_general_score": 42.5,
        "llmstats_general_rank": 20,
        "llmstats_coding_score": 23.8,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 43.333333333333336,
        "llmstats_percentile": 26.666666666666668,
        "llmdex_score": 35,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 11,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 83.33333333333333,
        "agreement_label": "Moderate agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 46.875,
        "llmstats_coding_percentile": 6.25,
        "llmdex_coding_score": 26.5625,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 14,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-7-plus",
        "canonical_family_name": "Qwen3.7 Plus",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-7-plus:default",
        "aa_representative_name": "Qwen3.7 Plus",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 39,
        "aa_rank": 47,
        "aa_official_coding_index": 53,
        "llmstats_source_name": "Qwen3.7-Plus",
        "llmstats_source_model_id": "qwen3.7-plus",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.7-plus",
        "llmstats_general_score": 43.8,
        "llmstats_general_rank": 15.5,
        "llmstats_coding_score": 32.7,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.4,
        "output_cost": 1.6,
        "tokens_per_second": 54,
        "latency": 2.89,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 13.333333333333334,
        "llmstats_percentile": 43.333333333333336,
        "llmdex_score": 28.333333333333336,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 12,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 70,
        "agreement_label": "Low agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 25,
        "llmstats_coding_percentile": 31.25,
        "llmdex_coding_score": 28.125,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 12.5,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-6-plus",
        "canonical_family_name": "Qwen3.6 Plus",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-6-plus:default",
        "aa_representative_name": "Qwen3.6 Plus",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 40,
        "aa_rank": 46,
        "aa_official_coding_index": 51,
        "llmstats_source_name": "Qwen3.6 Plus",
        "llmstats_source_model_id": "qwen3.6-plus",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.6-plus",
        "llmstats_general_score": 40.4,
        "llmstats_general_rank": 23,
        "llmstats_coding_score": 29.3,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.5,
        "output_cost": 3,
        "tokens_per_second": 53,
        "latency": 2.61,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 23.333333333333332,
        "llmstats_percentile": 20,
        "llmdex_score": 21.666666666666664,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 13,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 96.66666666666667,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 18.75,
        "llmstats_coding_percentile": 18.75,
        "llmdex_coding_score": 18.75,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 15,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "deepseek/deepseek-v4-flash",
        "canonical_family_name": "DeepSeek V4 Flash",
        "provider": "DeepSeek",
        "aa_representative_variant_id": "deepseek/deepseek-v4-flash:max",
        "aa_representative_name": "DeepSeek V4 Flash (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 40,
        "aa_rank": 45,
        "aa_official_coding_index": 53.5,
        "llmstats_source_name": "DeepSeek-V4-Flash-Max",
        "llmstats_source_model_id": "deepseek-v4-flash-max",
        "llmstats_source_model_url": "https://llm-stats.com/models/deepseek-v4-flash-max",
        "llmstats_general_score": 39.7,
        "llmstats_general_rank": 25,
        "llmstats_coding_score": 29.4,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.14,
        "output_cost": 0.28,
        "tokens_per_second": 121,
        "latency": 1.16,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 23.333333333333332,
        "llmstats_percentile": 13.333333333333334,
        "llmdex_score": 18.333333333333332,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 14,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 90,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 31.25,
        "llmstats_coding_percentile": 25,
        "llmdex_coding_score": 28.125,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 12.5,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-397b-a17b",
        "canonical_family_name": "Qwen3.5 397B A17B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-397b-a17b:default",
        "aa_representative_name": "Qwen3.5 397B A17B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 34,
        "aa_rank": 66,
        "aa_official_coding_index": 46.5,
        "llmstats_source_name": "Qwen3.5-397B-A17B",
        "llmstats_source_model_id": "qwen3.5-397b-a17b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.5-397b-a17b",
        "llmstats_general_score": 39.6,
        "llmstats_general_rank": 26,
        "llmstats_coding_score": 23.1,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.6,
        "output_cost": 3.6,
        "tokens_per_second": 68,
        "latency": 2.37,
        "context_window": 262000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 3.3333333333333335,
        "llmstats_percentile": 6.666666666666667,
        "llmdex_score": 5,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 15,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 96.66666666666667,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 6.25,
        "llmstats_coding_percentile": 0,
        "llmdex_coding_score": 3.125,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 17,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-sonnet-4-6",
        "canonical_family_name": "Claude Sonnet 4.6",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-sonnet-4-6:low-non-reasoning",
        "aa_representative_name": "Claude Sonnet 4.6 (Non-reasoning, Low Effort)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 34,
        "aa_rank": 62,
        "aa_official_coding_index": 44,
        "llmstats_source_name": "Claude Sonnet 4.6",
        "llmstats_source_model_id": "claude-sonnet-4-6",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-sonnet-4-6",
        "llmstats_general_score": 38.4,
        "llmstats_general_rank": 28,
        "llmstats_coding_score": 27.6,
        "score_status": "consensus",
        "score_status_label": "Consensus",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 3,
        "output_cost": 15,
        "tokens_per_second": 44,
        "latency": 1.37,
        "context_window": 1000000,
        "source_coverage": 2,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_percentile": 3.3333333333333335,
        "llmstats_percentile": 0,
        "llmdex_score": 1.6666666666666667,
        "llmdex_score_version": "LLMDEX General Consensus v1",
        "llmdex_score_scope": "confidently_matched_family_intersection",
        "llmdex_score_matched_population_size": 16,
        "llmdex_rank": 16,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "confidently_matched_family_intersection",
        "matched_population_size": 16,
        "agreement": 96.66666666666667,
        "agreement_label": "High agreement",
        "coding_score_status": "consensus",
        "aa_coding_percentile": 0,
        "llmstats_coding_percentile": 12.5,
        "llmdex_coding_score": 6.25,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 16,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/10gpt-5",
        "canonical_family_name": "10GPT-5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "10GPT-5",
        "llmstats_source_model_id": "gpt-5-2025-08-07",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5-2025-08-07",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/11gpt-5-1",
        "canonical_family_name": "11GPT-5.1",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "11GPT-5.1 Thinking",
        "llmstats_source_model_id": "gpt-5.1-thinking-2025-11-12",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.1-thinking-2025-11-12",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/12gpt-5-1-instant",
        "canonical_family_name": "12GPT-5.1 Instant",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "12GPT-5.1 Instant",
        "llmstats_source_model_id": "gpt-5.1-instant-2025-11-12",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.1-instant-2025-11-12",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/12mistral-small-4",
        "canonical_family_name": "12Mistral Small 4",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "12Mistral Small 4",
        "llmstats_source_model_id": "mistral-small-latest",
        "llmstats_source_model_url": "https://llm-stats.com/models/mistral-small-latest",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/13minimax-m1-40k",
        "canonical_family_name": "13MiniMax M1 40K",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "13MiniMax M1 40K",
        "llmstats_source_model_id": "minimax-m1-40k",
        "llmstats_source_model_url": "https://llm-stats.com/models/minimax-m1-40k",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/14hermes-3-70b",
        "canonical_family_name": "14Hermes 3 70B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "14Hermes 3 70B",
        "llmstats_source_model_id": "hermes-3-70b",
        "llmstats_source_model_url": "https://llm-stats.com/models/hermes-3-70b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/14qwen3-5-27b",
        "canonical_family_name": "14Qwen3.5-27B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "14Qwen3.5-27B",
        "llmstats_source_model_id": "qwen3.5-27b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.5-27b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/15nemotron-3-ultra-550b-a55b",
        "canonical_family_name": "15Nemotron 3 Ultra (550B A55B)",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "15Nemotron 3 Ultra (550B A55B)",
        "llmstats_source_model_id": "nemotron-3-ultra-550b-a55b",
        "llmstats_source_model_url": "https://llm-stats.com/models/nemotron-3-ultra-550b-a55b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/16nova-2-lite",
        "canonical_family_name": "16Nova 2 Lite",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "16Nova 2 Lite",
        "llmstats_source_model_id": "nova-2-lite",
        "llmstats_source_model_url": "https://llm-stats.com/models/nova-2-lite",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/17claude-haiku-4-5",
        "canonical_family_name": "17Claude Haiku 4.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "17Claude Haiku 4.5",
        "llmstats_source_model_id": "claude-haiku-4-5-20251001",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-haiku-4-5-20251001",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/18claude-opus-4",
        "canonical_family_name": "18Claude Opus 4",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "18Claude Opus 4",
        "llmstats_source_model_id": "claude-opus-4-20250514",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-20250514",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/18minimax-m1-80k",
        "canonical_family_name": "18MiniMax M1 80K",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "18MiniMax M1 80K",
        "llmstats_source_model_id": "minimax-m1-80k",
        "llmstats_source_model_url": "https://llm-stats.com/models/minimax-m1-80k",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/19glm-4-5-air",
        "canonical_family_name": "19GLM-4.5-Air",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "19GLM-4.5-Air",
        "llmstats_source_model_id": "glm-4.5-air",
        "llmstats_source_model_url": "https://llm-stats.com/models/glm-4.5-air",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/20glm-4-5",
        "canonical_family_name": "20GLM-4.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "20GLM-4.5",
        "llmstats_source_model_id": "glm-4.5",
        "llmstats_source_model_url": "https://llm-stats.com/models/glm-4.5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/20gpt-5-3-codex",
        "canonical_family_name": "20GPT-5.3 Codex",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "20GPT-5.3 Codex",
        "llmstats_source_model_id": "gpt-5.3-codex",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.3-codex",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/20qwen3-5-35b-a3b",
        "canonical_family_name": "20Qwen3.5-35B-A3B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "20Qwen3.5-35B-A3B",
        "llmstats_source_model_id": "qwen3.5-35b-a3b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.5-35b-a3b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/21claude-sonnet-4",
        "canonical_family_name": "21Claude Sonnet 4",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "21Claude Sonnet 4",
        "llmstats_source_model_id": "claude-sonnet-4-20250514",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-sonnet-4-20250514",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/21kimi-k2-thinking-0905",
        "canonical_family_name": "21Kimi K2-Thinking-0905",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "21Kimi K2-Thinking-0905",
        "llmstats_source_model_id": "kimi-k2-thinking-0905",
        "llmstats_source_model_url": "https://llm-stats.com/models/kimi-k2-thinking-0905",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/22mai-thinking-1",
        "canonical_family_name": "22MAI-Thinking-1",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "22MAI-Thinking-1",
        "llmstats_source_model_id": "mai-thinking-1",
        "llmstats_source_model_url": "https://llm-stats.com/models/mai-thinking-1",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/22qwen2-5-72b-instruct",
        "canonical_family_name": "22Qwen2.5 72B Instruct",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "22Qwen2.5 72B Instruct",
        "llmstats_source_model_id": "qwen-2.5-72b-instruct",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen-2.5-72b-instruct",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/23mimo-v2-pro",
        "canonical_family_name": "23MiMo-V2-Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "23MiMo-V2-Pro",
        "llmstats_source_model_id": "mimo-v2-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/mimo-v2-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/24claude-opus-4-1",
        "canonical_family_name": "24Claude Opus 4.1",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "24Claude Opus 4.1",
        "llmstats_source_model_id": "claude-opus-4-1-20250805",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-1-20250805",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/24qwen3-6-35b-a3b",
        "canonical_family_name": "24Qwen3.6-35B-A3B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "24Qwen3.6-35B-A3B",
        "llmstats_source_model_id": "qwen3.6-35b-a3b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.6-35b-a3b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/25claude-3-7-sonnet",
        "canonical_family_name": "25Claude 3.7 Sonnet",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "25Claude 3.7 Sonnet",
        "llmstats_source_model_id": "claude-3-7-sonnet-20250219",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-3-7-sonnet-20250219",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/25gpt-5-5-pro",
        "canonical_family_name": "25GPT-5.5 Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "25GPT-5.5 Pro",
        "llmstats_source_model_id": "gpt-5.5-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.5-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/26gemma-2-27b",
        "canonical_family_name": "26Gemma 2 27B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "26Gemma 2 27B",
        "llmstats_source_model_id": "gemma-2-27b-it",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemma-2-27b-it",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/26longcat-flash",
        "canonical_family_name": "26LongCat-Flash",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "26LongCat-Flash-Thinking",
        "llmstats_source_model_id": "longcat-flash-thinking",
        "llmstats_source_model_url": "https://llm-stats.com/models/longcat-flash-thinking",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/27o3",
        "canonical_family_name": "27o3",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "27o3",
        "llmstats_source_model_id": "o3-2025-04-16",
        "llmstats_source_model_url": "https://llm-stats.com/models/o3-2025-04-16",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/27qwen3-5-9b",
        "canonical_family_name": "27Qwen3.5-9B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "27Qwen3.5-9B",
        "llmstats_source_model_id": "qwen3.5-9b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.5-9b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/28qwen3-vl-235b-a22b",
        "canonical_family_name": "28Qwen3 VL 235B A22B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "28Qwen3 VL 235B A22B Thinking",
        "llmstats_source_model_id": "qwen3-vl-235b-a22b-thinking",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3-vl-235b-a22b-thinking",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/28qwen3-6-27b",
        "canonical_family_name": "28Qwen3.6-27B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "28Qwen3.6-27B",
        "llmstats_source_model_id": "qwen3.6-27b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.6-27b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/29gemini-2-5-pro",
        "canonical_family_name": "29Gemini 2.5 Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "29Gemini 2.5 Pro",
        "llmstats_source_model_id": "gemini-2.5-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-2.5-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/29kimi-k2-5",
        "canonical_family_name": "29Kimi K2.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "29Kimi K2.5",
        "llmstats_source_model_id": "kimi-k2.5",
        "llmstats_source_model_url": "https://llm-stats.com/models/kimi-k2.5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/29llama-3-1-70b-instruct",
        "canonical_family_name": "29Llama 3.1 70B Instruct",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "29Llama 3.1 70B Instruct",
        "llmstats_source_model_id": "llama-3.1-70b-instruct",
        "llmstats_source_model_url": "https://llm-stats.com/models/llama-3.1-70b-instruct",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/29minimax-m2-5",
        "canonical_family_name": "29MiniMax M2.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "29MiniMax M2.5",
        "llmstats_source_model_id": "minimax-m2.5",
        "llmstats_source_model_url": "https://llm-stats.com/models/minimax-m2.5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/29qwen3-coder-480b-a35b-instruct",
        "canonical_family_name": "29Qwen3-Coder 480B A35B Instruct",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "29Qwen3-Coder 480B A35B Instruct",
        "llmstats_source_model_id": "qwen3-coder-480b-a35b-instruct",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3-coder-480b-a35b-instruct",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/2longcat-flash-thinking-2601",
        "canonical_family_name": "2LongCat-Flash-Thinking-2601",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "2LongCat-Flash-Thinking-2601",
        "llmstats_source_model_id": "longcat-flash-thinking-2601",
        "llmstats_source_model_url": "https://llm-stats.com/models/longcat-flash-thinking-2601",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/30qwen3-5-122b-a10b",
        "canonical_family_name": "30Qwen3.5-122B-A10B",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "30Qwen3.5-122B-A10B",
        "llmstats_source_model_id": "qwen3.5-122b-a10b",
        "llmstats_source_model_url": "https://llm-stats.com/models/qwen3.5-122b-a10b",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/3claude-opus-4-5",
        "canonical_family_name": "3Claude Opus 4.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "3Claude Opus 4.5",
        "llmstats_source_model_id": "claude-opus-4-5-20251101",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-5-20251101",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/5claude-sonnet-4-5",
        "canonical_family_name": "5Claude Sonnet 4.5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "5Claude Sonnet 4.5",
        "llmstats_source_model_id": "claude-sonnet-4-5-20250929",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-sonnet-4-5-20250929",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/8llama-3-1-405b-instruct",
        "canonical_family_name": "8Llama 3.1 405B Instruct",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "8Llama 3.1 405B Instruct",
        "llmstats_source_model_id": "llama-3.1-405b-instruct",
        "llmstats_source_model_url": "https://llm-stats.com/models/llama-3.1-405b-instruct",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/8nova-2-pro",
        "canonical_family_name": "8Nova 2 Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "8Nova 2 Pro",
        "llmstats_source_model_id": "nova-2-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/nova-2-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/9nova-2-omni",
        "canonical_family_name": "9Nova 2 Omni",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "9Nova 2 Omni",
        "llmstats_source_model_id": "nova-2-omni",
        "llmstats_source_model_url": "https://llm-stats.com/models/nova-2-omni",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "sapiens-ai/agnes-2-5-pro-alpha",
        "canonical_family_name": "Agnes 2.5 Pro Alpha",
        "provider": "Sapiens AI",
        "aa_representative_variant_id": "sapiens-ai/agnes-2-5-pro-alpha:default",
        "aa_representative_name": "Agnes 2.5 Pro Alpha",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 39,
        "aa_rank": 49,
        "aa_official_coding_index": 54.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.45,
        "output_cost": 0.9,
        "tokens_per_second": 132,
        "latency": 2.23,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "swiss-ai-initiative/apertus-70b-instruct",
        "canonical_family_name": "Apertus 70B Instruct",
        "provider": "Swiss AI Initiative",
        "aa_representative_variant_id": "swiss-ai-initiative/apertus-70b-instruct:default",
        "aa_representative_name": "Apertus 70B Instruct",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 245,
        "aa_official_coding_index": 6,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.82,
        "output_cost": 2.92,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "swiss-ai-initiative/apertus-8b-instruct",
        "canonical_family_name": "Apertus 8B Instruct",
        "provider": "Swiss AI Initiative",
        "aa_representative_variant_id": "swiss-ai-initiative/apertus-8b-instruct:default",
        "aa_representative_name": "Apertus 8B Instruct",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 1,
        "aa_rank": 254,
        "aa_official_coding_index": 4,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.2,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "servicenow/apriel-v1-6-15b-thinker",
        "canonical_family_name": "Apriel-v1.6-15B-Thinker",
        "provider": "ServiceNow",
        "aa_representative_variant_id": "servicenow/apriel-v1-6-15b-thinker:default",
        "aa_representative_name": "Apriel-v1.6-15B-Thinker",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 21,
        "aa_rank": 114,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-4-5-haiku",
        "canonical_family_name": "Claude 4.5 Haiku",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-4-5-haiku:reasoning",
        "aa_representative_name": "Claude 4.5 Haiku (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 30,
        "aa_rank": 81,
        "aa_official_coding_index": 43.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1,
        "output_cost": 5,
        "tokens_per_second": 92,
        "latency": 11.93,
        "context_window": 200000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-fable-5",
        "canonical_family_name": "Claude Fable 5",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-fable-5:fallback",
        "aa_representative_name": "Claude Fable 5 (with fallback)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 60,
        "aa_rank": 3,
        "aa_official_coding_index": 72.5,
        "llmstats_source_name": "Claude Fable 5",
        "llmstats_source_model_id": "claude-fable-5",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-fable-5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 48.4,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 10,
        "output_cost": 50,
        "tokens_per_second": 71,
        "latency": 112.25,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "matched",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "consensus",
        "aa_coding_percentile": 100,
        "llmstats_coding_percentile": 93.75,
        "llmdex_coding_score": 96.875,
        "llmdex_coding_score_version": "LLMDEX Coding Consensus v1",
        "llmdex_coding_score_scope": "confidently_matched_family_coding_intersection",
        "llmdex_coding_score_matched_population_size": 17,
        "llmdex_coding_rank": 1,
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-mythos-preview",
        "canonical_family_name": "Claude Mythos Preview",
        "provider": "Anthropic",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Claude Mythos Preview",
        "llmstats_source_model_id": "claude-mythos-preview",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-mythos-preview",
        "llmstats_general_score": 56.1,
        "llmstats_general_rank": 2,
        "llmstats_coding_score": 46.6,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-opus-4-6",
        "canonical_family_name": "Claude Opus 4.6",
        "provider": "Anthropic",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Claude Opus 4.6",
        "llmstats_source_model_id": "claude-opus-4-6",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-4-6",
        "llmstats_general_score": 46.4,
        "llmstats_general_rank": 11,
        "llmstats_coding_score": 35.1,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-opus-5",
        "canonical_family_name": "Claude Opus 5",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-opus-5:max",
        "aa_representative_name": "Claude Opus 5 (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 61,
        "aa_rank": 1,
        "aa_official_coding_index": 72.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 5,
        "output_cost": 25,
        "tokens_per_second": 53,
        "latency": 68.04,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/claude-opus-5",
        "canonical_family_name": "Claude Opus 5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Claude Opus 5",
        "llmstats_source_model_id": "claude-opus-5",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-opus-5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 42.7,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-sonnet-5",
        "canonical_family_name": "Claude Sonnet 5",
        "provider": "Anthropic",
        "aa_representative_variant_id": "anthropic/claude-sonnet-5:max",
        "aa_representative_name": "Claude Sonnet 5 (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 53,
        "aa_rank": 14,
        "aa_official_coding_index": 67.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 10,
        "tokens_per_second": 76,
        "latency": 192.06,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/claude-sonnet-5",
        "canonical_family_name": "Claude Sonnet 5",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Claude Sonnet 5",
        "llmstats_source_model_id": "claude-sonnet-5",
        "llmstats_source_model_url": "https://llm-stats.com/models/claude-sonnet-5",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 40.4,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "deep-cogito/cogito-v2-1",
        "canonical_family_name": "Cogito v2.1",
        "provider": "Deep Cogito",
        "aa_representative_variant_id": "deep-cogito/cogito-v2-1:reasoning",
        "aa_representative_name": "Cogito v2.1 (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": null,
        "aa_rank": 263,
        "aa_official_coding_index": 41,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.25,
        "output_cost": 1.25,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "cohere/command-a",
        "canonical_family_name": "Command A+",
        "provider": "Cohere",
        "aa_representative_variant_id": "cohere/command-a:default",
        "aa_representative_name": "Command A+",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 23,
        "aa_rank": 104,
        "aa_official_coding_index": 30.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 196,
        "latency": 0.42,
        "context_window": 192000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nous-research/deephermes-3-llama-3-1-8b",
        "canonical_family_name": "DeepHermes 3 - Llama-3.1 8B",
        "provider": "Nous Research",
        "aa_representative_variant_id": "nous-research/deephermes-3-llama-3-1-8b:default",
        "aa_representative_name": "DeepHermes 3 - Llama-3.1 8B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 247,
        "aa_official_coding_index": 9,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nous-research/deephermes-3-mistral-24b",
        "canonical_family_name": "DeepHermes 3 - Mistral 24B",
        "provider": "Nous Research",
        "aa_representative_variant_id": "nous-research/deephermes-3-mistral-24b:default",
        "aa_representative_name": "DeepHermes 3 - Mistral 24B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 218,
        "aa_official_coding_index": 23,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/devstral-2",
        "canonical_family_name": "Devstral 2",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/devstral-2:default",
        "aa_representative_name": "Devstral 2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 19,
        "aa_rank": 122,
        "aa_official_coding_index": 31.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 20,
        "latency": 1.31,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/devstral-small-2",
        "canonical_family_name": "Devstral Small 2",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/devstral-small-2:default",
        "aa_representative_name": "Devstral Small 2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 17,
        "aa_rank": 132,
        "aa_official_coding_index": 29.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 20,
        "latency": 1.52,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/diffusiongemma-26b-a4b",
        "canonical_family_name": "DiffusionGemma 26B A4B",
        "provider": "Google",
        "aa_representative_variant_id": "google/diffusiongemma-26b-a4b:default",
        "aa_representative_name": "DiffusionGemma 26B A4B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 13,
        "aa_rank": 157,
        "aa_official_coding_index": 23,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "bytedance-seed/doubao-seed-code",
        "canonical_family_name": "Doubao Seed Code",
        "provider": "ByteDance Seed",
        "aa_representative_variant_id": "bytedance-seed/doubao-seed-code:default",
        "aa_representative_name": "Doubao Seed Code",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 26,
        "aa_rank": 93,
        "aa_official_coding_index": 41,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "baidu/ernie-4-5-300b-a47b",
        "canonical_family_name": "ERNIE 4.5 300B A47B",
        "provider": "Baidu",
        "aa_representative_variant_id": "baidu/ernie-4-5-300b-a47b:default",
        "aa_representative_name": "ERNIE 4.5 300B A47B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 183,
        "aa_official_coding_index": 31,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.28,
        "output_cost": 1.1,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "baidu/ernie-5-0-thinking-preview",
        "canonical_family_name": "ERNIE 5.0 Thinking Preview",
        "provider": "Baidu",
        "aa_representative_variant_id": "baidu/ernie-5-0-thinking-preview:thinking-preview",
        "aa_representative_name": "ERNIE 5.0 Thinking Preview",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 22,
        "aa_rank": 106,
        "aa_official_coding_index": 38,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "lg-ai-research/exaone-4-0-1-2b",
        "canonical_family_name": "Exaone 4.0 1.2B",
        "provider": "LG AI Research",
        "aa_representative_variant_id": "lg-ai-research/exaone-4-0-1-2b:reasoning",
        "aa_representative_name": "Exaone 4.0 1.2B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 236,
        "aa_official_coding_index": 9,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 64000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "lg-ai-research/exaone-4-0-32b",
        "canonical_family_name": "EXAONE 4.0 32B",
        "provider": "LG AI Research",
        "aa_representative_variant_id": "lg-ai-research/exaone-4-0-32b:reasoning",
        "aa_representative_name": "EXAONE 4.0 32B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 11,
        "aa_rank": 173,
        "aa_official_coding_index": 34,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "lg-ai-research/exaone-4-5-33b",
        "canonical_family_name": "EXAONE 4.5 33B",
        "provider": "LG AI Research",
        "aa_representative_variant_id": "lg-ai-research/exaone-4-5-33b:default",
        "aa_representative_name": "EXAONE 4.5 33B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 20,
        "aa_rank": 116,
        "aa_official_coding_index": 24.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "tii-uae/falcon-h1r-7b",
        "canonical_family_name": "Falcon-H1R-7B",
        "provider": "TII UAE",
        "aa_representative_variant_id": "tii-uae/falcon-h1r-7b:default",
        "aa_representative_name": "Falcon-H1R-7B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 10,
        "aa_rank": 177,
        "aa_official_coding_index": 25,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ai9stars/g9v3-3b",
        "canonical_family_name": "G9v3-3B",
        "provider": "AI9Stars",
        "aa_representative_variant_id": "ai9stars/g9v3-3b:default",
        "aa_representative_name": "G9v3-3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 16,
        "aa_rank": 140,
        "aa_official_coding_index": 12,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-2-5-pro",
        "canonical_family_name": "Gemini 2.5 Pro",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-2-5-pro:default",
        "aa_representative_name": "Gemini 2.5 Pro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 26,
        "aa_rank": 94,
        "aa_official_coding_index": 35.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.25,
        "output_cost": 10,
        "tokens_per_second": 128,
        "latency": 23.37,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-deep-think",
        "canonical_family_name": "Gemini 3 Deep Think",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-deep-think:default",
        "aa_representative_name": "Gemini 3 Deep Think",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": null,
        "aa_rank": 259,
        "aa_official_coding_index": null,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-flash",
        "canonical_family_name": "Gemini 3 Flash",
        "provider": "Google",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Gemini 3 Flash",
        "llmstats_source_model_id": "gemini-3-flash-preview",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-3-flash-preview",
        "llmstats_general_score": 37.7,
        "llmstats_general_rank": 29,
        "llmstats_coding_score": 22.8,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "ambiguous",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-pro",
        "canonical_family_name": "Gemini 3 Pro",
        "provider": "Google",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Gemini 3 Pro",
        "llmstats_source_model_id": "gemini-3-pro-preview",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-3-pro-preview",
        "llmstats_general_score": 39.1,
        "llmstats_general_rank": 27,
        "llmstats_coding_score": 24.5,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-1-flash-lite",
        "canonical_family_name": "Gemini 3.1 Flash-Lite",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-1-flash-lite:default",
        "aa_representative_name": "Gemini 3.1 Flash-Lite",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 25,
        "aa_rank": 97,
        "aa_official_coding_index": 36.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 1.5,
        "tokens_per_second": 293,
        "latency": 6.12,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-5-flash",
        "canonical_family_name": "Gemini 3.5 Flash",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-5-flash:default",
        "aa_representative_name": "Gemini 3.5 Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 50,
        "aa_rank": 20,
        "aa_official_coding_index": 66,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.5,
        "output_cost": 9,
        "tokens_per_second": 185,
        "latency": 22.21,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/gemini-3-5-flash",
        "canonical_family_name": "Gemini 3.5 Flash",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Gemini 3.5 Flash",
        "llmstats_source_model_id": "gemini-3.5-flash",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-3.5-flash",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 34.2,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-5-flash-lite",
        "canonical_family_name": "Gemini 3.5 Flash-Lite",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-5-flash-lite:default",
        "aa_representative_name": "Gemini 3.5 Flash-Lite",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 36,
        "aa_rank": 55,
        "aa_official_coding_index": 47.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 2.5,
        "tokens_per_second": 399,
        "latency": 9.4,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-6-flash",
        "canonical_family_name": "Gemini 3.6 Flash",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemini-3-6-flash:default",
        "aa_representative_name": "Gemini 3.6 Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 50,
        "aa_rank": 21,
        "aa_official_coding_index": 65.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.5,
        "output_cost": 7.5,
        "tokens_per_second": 231,
        "latency": 18.59,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/gemini-3-6-flash",
        "canonical_family_name": "Gemini 3.6 Flash",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Gemini 3.6 Flash",
        "llmstats_source_model_id": "gemini-3.6-flash",
        "llmstats_source_model_url": "https://llm-stats.com/models/gemini-3.6-flash",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 32.8,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-3-270m",
        "canonical_family_name": "Gemma 3 270M",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-3-270m:default",
        "aa_representative_name": "Gemma 3 270M",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 244,
        "aa_official_coding_index": 0,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-4-12b",
        "canonical_family_name": "Gemma 4 12B",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-4-12b:default",
        "aa_representative_name": "Gemma 4 12B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 22,
        "aa_rank": 107,
        "aa_official_coding_index": 32.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.3,
        "tokens_per_second": 110,
        "latency": 2.39,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-4-26b-a4b",
        "canonical_family_name": "Gemma 4 26B A4B",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-4-26b-a4b:default",
        "aa_representative_name": "Gemma 4 26B A4B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 26,
        "aa_rank": 95,
        "aa_official_coding_index": 39.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.13,
        "output_cost": 0.4,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-4-31b",
        "canonical_family_name": "Gemma 4 31B",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-4-31b:default",
        "aa_representative_name": "Gemma 4 31B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 29,
        "aa_rank": 82,
        "aa_official_coding_index": 43,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 35,
        "latency": 1.03,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-4-e2b",
        "canonical_family_name": "Gemma 4 E2B",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-4-e2b:default",
        "aa_representative_name": "Gemma 4 E2B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 179,
        "aa_official_coding_index": 10.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemma-4-e4b",
        "canonical_family_name": "Gemma 4 E4B",
        "provider": "Google",
        "aa_representative_variant_id": "google/gemma-4-e4b:default",
        "aa_representative_name": "Gemma 4 E4B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 12,
        "aa_rank": 167,
        "aa_official_coding_index": 13,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.02,
        "output_cost": 0.1,
        "tokens_per_second": 91,
        "latency": 0.8,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/glm-5-1",
        "canonical_family_name": "GLM-5.1",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GLM-5.1",
        "llmstats_source_model_id": "glm-5.1",
        "llmstats_source_model_url": "https://llm-stats.com/models/glm-5.1",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 33.4,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "z-ai/glm-5-2",
        "canonical_family_name": "GLM-5.2",
        "provider": "Z AI",
        "aa_representative_variant_id": "z-ai/glm-5-2:max",
        "aa_representative_name": "GLM-5.2 (max)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 51,
        "aa_rank": 17,
        "aa_official_coding_index": 64,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.4,
        "output_cost": 4.4,
        "tokens_per_second": 191,
        "latency": 1.35,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "zai/glm-5-2",
        "canonical_family_name": "GLM-5.2",
        "provider": "ZAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GLM-5.2",
        "llmstats_source_model_id": "glm-5.2",
        "llmstats_source_model_url": "https://llm-stats.com/models/glm-5.2",
        "llmstats_general_score": 47.1,
        "llmstats_general_rank": 8,
        "llmstats_coding_score": 39,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-1",
        "canonical_family_name": "GPT-5.1",
        "provider": "OpenAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GPT-5.1",
        "llmstats_source_model_id": "gpt-5.1-2025-11-13",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.1-2025-11-13",
        "llmstats_general_score": 37.1,
        "llmstats_general_rank": 30,
        "llmstats_coding_score": 20.2,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-2",
        "canonical_family_name": "GPT-5.2",
        "provider": "OpenAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GPT-5.2",
        "llmstats_source_model_id": "gpt-5.2-2025-12-11",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.2-2025-12-11",
        "llmstats_general_score": 42.1,
        "llmstats_general_rank": 21,
        "llmstats_coding_score": 24.6,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-2-pro",
        "canonical_family_name": "GPT-5.2 Pro",
        "provider": "OpenAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GPT-5.2 Pro",
        "llmstats_source_model_id": "gpt-5.2-pro-2025-12-11",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.2-pro-2025-12-11",
        "llmstats_general_score": 43.2,
        "llmstats_general_rank": 19,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-3-codex",
        "canonical_family_name": "GPT-5.3 Codex",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-3-codex:xhigh",
        "aa_representative_name": "GPT-5.3 Codex (xhigh)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 44,
        "aa_rank": 32,
        "aa_official_coding_index": 53,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.75,
        "output_cost": 14,
        "tokens_per_second": 134,
        "latency": 66.05,
        "context_window": 400000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-4",
        "canonical_family_name": "GPT-5.4",
        "provider": "OpenAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GPT-5.4",
        "llmstats_source_model_id": "gpt-5.4",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.4",
        "llmstats_general_score": 43.7,
        "llmstats_general_rank": 17,
        "llmstats_coding_score": 34.2,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-5",
        "canonical_family_name": "GPT-5.5",
        "provider": "OpenAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "GPT-5.5",
        "llmstats_source_model_id": "gpt-5.5",
        "llmstats_source_model_url": "https://llm-stats.com/models/gpt-5.5",
        "llmstats_general_score": 49.1,
        "llmstats_general_rank": 7,
        "llmstats_coding_score": 41.1,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-5-instant-june-2026",
        "canonical_family_name": "GPT-5.5 Instant (June 2026)",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-5-instant-june-2026:default",
        "aa_representative_name": "GPT-5.5 Instant (June 2026)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 29,
        "aa_rank": 83,
        "aa_official_coding_index": 42,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 5,
        "output_cost": 30,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 400000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-5-pro",
        "canonical_family_name": "GPT-5.5 Pro",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-5-5-pro:xhigh",
        "aa_representative_name": "GPT-5.5 Pro (xhigh)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": null,
        "aa_rank": 262,
        "aa_official_coding_index": null,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 922000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-oss-120b",
        "canonical_family_name": "gpt-oss-120b",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-oss-120b:high",
        "aa_representative_name": "gpt-oss-120b (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 24,
        "aa_rank": 102,
        "aa_official_coding_index": 32.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.15,
        "output_cost": 0.6,
        "tokens_per_second": 273,
        "latency": 0.88,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-oss-20b",
        "canonical_family_name": "gpt-oss-20b",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/gpt-oss-20b:high",
        "aa_representative_name": "gpt-oss-20b (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 15,
        "aa_rank": 147,
        "aa_official_coding_index": 24,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.06,
        "output_cost": 0.2,
        "tokens_per_second": 219,
        "latency": 0.91,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-1b",
        "canonical_family_name": "Granite 4.0 1B",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-1b:default",
        "aa_representative_name": "Granite 4.0 1B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 248,
        "aa_official_coding_index": 9,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-350m",
        "canonical_family_name": "Granite 4.0 350M",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-350m:default",
        "aa_representative_name": "Granite 4.0 350M",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 1,
        "aa_rank": 252,
        "aa_official_coding_index": 1,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-h-1b",
        "canonical_family_name": "Granite 4.0 H 1B",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-h-1b:default",
        "aa_representative_name": "Granite 4.0 H 1B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 243,
        "aa_official_coding_index": 8,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-h-350m",
        "canonical_family_name": "Granite 4.0 H 350M",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-h-350m:default",
        "aa_representative_name": "Granite 4.0 H 350M",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 1,
        "aa_rank": 255,
        "aa_official_coding_index": 2,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-h-small",
        "canonical_family_name": "Granite 4.0 H Small",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-h-small:default",
        "aa_representative_name": "Granite 4.0 H Small",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 220,
        "aa_official_coding_index": 21,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.06,
        "output_cost": 0.25,
        "tokens_per_second": 407,
        "latency": 10.22,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-0-micro",
        "canonical_family_name": "Granite 4.0 Micro",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-0-micro:default",
        "aa_representative_name": "Granite 4.0 Micro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 246,
        "aa_official_coding_index": 12,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-1-30b",
        "canonical_family_name": "Granite 4.1 30B",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-1-30b:default",
        "aa_representative_name": "Granite 4.1 30B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 189,
        "aa_official_coding_index": 14.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-1-3b",
        "canonical_family_name": "Granite 4.1 3B",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-1-3b:default",
        "aa_representative_name": "Granite 4.1 3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 225,
        "aa_official_coding_index": 6.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ibm/granite-4-1-8b",
        "canonical_family_name": "Granite 4.1 8B",
        "provider": "IBM",
        "aa_representative_variant_id": "ibm/granite-4-1-8b:default",
        "aa_representative_name": "Granite 4.1 8B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 7,
        "aa_rank": 207,
        "aa_official_coding_index": 12.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.05,
        "output_cost": 0.1,
        "tokens_per_second": 112,
        "latency": 0.8,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "spacexai/grok-4-3",
        "canonical_family_name": "Grok 4.3",
        "provider": "SpaceXAI",
        "aa_representative_variant_id": "spacexai/grok-4-3:medium",
        "aa_representative_name": "Grok 4.3 (medium)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 36,
        "aa_rank": 57,
        "aa_official_coding_index": 45,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.25,
        "output_cost": 2.5,
        "tokens_per_second": 106,
        "latency": 15.66,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "spacexai/grok-4-5",
        "canonical_family_name": "Grok 4.5",
        "provider": "SpaceXAI",
        "aa_representative_variant_id": "spacexai/grok-4-5:high",
        "aa_representative_name": "Grok 4.5 (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 54,
        "aa_rank": 12,
        "aa_official_coding_index": 68,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 6,
        "tokens_per_second": 61,
        "latency": 10.26,
        "context_window": 500000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xai/grok-4-5",
        "canonical_family_name": "Grok 4.5",
        "provider": "xAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Grok 4.5",
        "llmstats_source_model_id": "grok-4.5",
        "llmstats_source_model_url": "https://llm-stats.com/models/grok-4.5",
        "llmstats_general_score": 49.5,
        "llmstats_general_rank": 6,
        "llmstats_coding_score": 40.5,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xai/grok-4-heavy",
        "canonical_family_name": "Grok-4 Heavy",
        "provider": "xAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Grok-4 Heavy",
        "llmstats_source_model_id": "grok-4-heavy",
        "llmstats_source_model_url": "https://llm-stats.com/models/grok-4-heavy",
        "llmstats_general_score": 41.4,
        "llmstats_general_rank": 22,
        "llmstats_coding_score": 18.4,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nous-research/hermes-4-405b",
        "canonical_family_name": "Hermes 4 405B",
        "provider": "Nous Research",
        "aa_representative_variant_id": "nous-research/hermes-4-405b:reasoning",
        "aa_representative_name": "Hermes 4 405B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 184,
        "aa_official_coding_index": 25,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1,
        "output_cost": 3,
        "tokens_per_second": 39,
        "latency": 2.37,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nous-research/hermes-4-70b",
        "canonical_family_name": "Hermes 4 70B",
        "provider": "Nous Research",
        "aa_representative_variant_id": "nous-research/hermes-4-70b:reasoning",
        "aa_representative_name": "Hermes 4 70B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 10,
        "aa_rank": 176,
        "aa_official_coding_index": 34,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.13,
        "output_cost": 0.4,
        "tokens_per_second": 93,
        "latency": 1.37,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "tencent/hy3-preview",
        "canonical_family_name": "Hy3-preview",
        "provider": "Tencent",
        "aa_representative_variant_id": "tencent/hy3-preview:preview",
        "aa_representative_name": "Hy3-preview",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 34,
        "aa_rank": 67,
        "aa_official_coding_index": 41,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.06,
        "output_cost": 0.23,
        "tokens_per_second": 131,
        "latency": 3.22,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "naver/hyperclova-x-seed-think-32b",
        "canonical_family_name": "HyperCLOVA X SEED Think (32B)",
        "provider": "Naver",
        "aa_representative_variant_id": "naver/hyperclova-x-seed-think-32b:default",
        "aa_representative_name": "HyperCLOVA X SEED Think (32B)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 17,
        "aa_rank": 135,
        "aa_official_coding_index": 28,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "multiverse-computing/hypernova-60b-2605",
        "canonical_family_name": "HyperNova 60B 2605",
        "provider": "Multiverse Computing",
        "aa_representative_variant_id": "multiverse-computing/hypernova-60b-2605:default",
        "aa_representative_name": "HyperNova 60B 2605",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 18,
        "aa_rank": 130,
        "aa_official_coding_index": 25.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.04,
        "output_cost": 0.14,
        "tokens_per_second": 414,
        "latency": 0.65,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "thinking-machines/inkling",
        "canonical_family_name": "Inkling",
        "provider": "Thinking Machines",
        "aa_representative_variant_id": "thinking-machines/inkling:default",
        "aa_representative_name": "Inkling",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 41,
        "aa_rank": 43,
        "aa_official_coding_index": 50.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.87,
        "output_cost": 4.68,
        "tokens_per_second": 82,
        "latency": 1.79,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "prime-intellect/intellect-3",
        "canonical_family_name": "INTELLECT-3",
        "provider": "Prime Intellect",
        "aa_representative_variant_id": "prime-intellect/intellect-3:default",
        "aa_representative_name": "INTELLECT-3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 16,
        "aa_rank": 143,
        "aa_official_coding_index": 39,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ai21-labs/jamba-1-7-large",
        "canonical_family_name": "Jamba 1.7 Large",
        "provider": "AI21 Labs",
        "aa_representative_variant_id": "ai21-labs/jamba-1-7-large:default",
        "aa_representative_name": "Jamba 1.7 Large",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 219,
        "aa_official_coding_index": 19,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 8,
        "tokens_per_second": 54,
        "latency": 1.4,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ai21-labs/jamba-1-7-mini",
        "canonical_family_name": "Jamba 1.7 Mini",
        "provider": "AI21 Labs",
        "aa_representative_variant_id": "ai21-labs/jamba-1-7-mini:default",
        "aa_representative_name": "Jamba 1.7 Mini",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 240,
        "aa_official_coding_index": 9,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 258000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "ai21-labs/jamba-reasoning-3b",
        "canonical_family_name": "Jamba Reasoning 3B",
        "provider": "AI21 Labs",
        "aa_representative_variant_id": "ai21-labs/jamba-reasoning-3b:reasoning",
        "aa_representative_name": "Jamba Reasoning 3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 229,
        "aa_official_coding_index": 6,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "china-mobile/jt-35b-flash",
        "canonical_family_name": "JT-35B-Flash",
        "provider": "China Mobile",
        "aa_representative_variant_id": "china-mobile/jt-35b-flash:default",
        "aa_representative_name": "JT-35B-Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 28,
        "aa_rank": 85,
        "aa_official_coding_index": 29,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "china-mobile/jt-4-1-flash-236b-a21b",
        "canonical_family_name": "JT-4.1 Flash 236B A21B",
        "provider": "China Mobile",
        "aa_representative_variant_id": "china-mobile/jt-4-1-flash-236b-a21b:default",
        "aa_representative_name": "JT-4.1 Flash 236B A21B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 39,
        "aa_rank": 48,
        "aa_official_coding_index": 49,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "china-mobile/jt-mini",
        "canonical_family_name": "JT-MINI",
        "provider": "China Mobile",
        "aa_representative_variant_id": "china-mobile/jt-mini:default",
        "aa_representative_name": "JT-MINI",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 19,
        "aa_rank": 125,
        "aa_official_coding_index": 27,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "lg-ai-research/k-exaone",
        "canonical_family_name": "K-EXAONE",
        "provider": "LG AI Research",
        "aa_representative_variant_id": "lg-ai-research/k-exaone:default",
        "aa_representative_name": "K-EXAONE",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 22,
        "aa_rank": 105,
        "aa_official_coding_index": 33,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mbzuai-institute-of-foundation-models/k2-think-v2",
        "canonical_family_name": "K2 Think V2",
        "provider": "MBZUAI Institute of Foundation Models",
        "aa_representative_variant_id": "mbzuai-institute-of-foundation-models/k2-think-v2:default",
        "aa_representative_name": "K2 Think V2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 17,
        "aa_rank": 133,
        "aa_official_coding_index": 24,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mbzuai-institute-of-foundation-models/k2-v2",
        "canonical_family_name": "K2-V2",
        "provider": "MBZUAI Institute of Foundation Models",
        "aa_representative_variant_id": "mbzuai-institute-of-foundation-models/k2-v2:high",
        "aa_representative_name": "K2-V2 (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 151,
        "aa_official_coding_index": 29,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 512000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "kwaikat/kat-coder-pro-v1",
        "canonical_family_name": "KAT-Coder-Pro V1",
        "provider": "KwaiKAT",
        "aa_representative_variant_id": "kwaikat/kat-coder-pro-v1:default",
        "aa_representative_name": "KAT-Coder-Pro V1",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 28,
        "aa_rank": 86,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "kwaikat/kat-coder-pro-v2",
        "canonical_family_name": "KAT-Coder-Pro V2",
        "provider": "KwaiKAT",
        "aa_representative_variant_id": "kwaikat/kat-coder-pro-v2:default",
        "aa_representative_name": "KAT-Coder-Pro V2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 34,
        "aa_rank": 65,
        "aa_official_coding_index": 54,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 1.2,
        "tokens_per_second": 100,
        "latency": 1.62,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "kimi/kimi-k2-6",
        "canonical_family_name": "Kimi K2.6",
        "provider": "Kimi",
        "aa_representative_variant_id": "kimi/kimi-k2-6:non-reasoning",
        "aa_representative_name": "Kimi K2.6 (non-reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 35,
        "aa_rank": 61,
        "aa_official_coding_index": 39,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.95,
        "output_cost": 4,
        "tokens_per_second": 36,
        "latency": 2.98,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "moonshot-ai/kimi-k2-6",
        "canonical_family_name": "Kimi K2.6",
        "provider": "MoonshotAI",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Kimi K2.6",
        "llmstats_source_model_id": "kimi-k2.6",
        "llmstats_source_model_url": "https://llm-stats.com/models/kimi-k2.6",
        "llmstats_general_score": 44.7,
        "llmstats_general_rank": 13,
        "llmstats_coding_score": 35.4,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "kimi/kimi-k2-7-code",
        "canonical_family_name": "Kimi K2.7 Code",
        "provider": "Kimi",
        "aa_representative_variant_id": "kimi/kimi-k2-7-code:default",
        "aa_representative_name": "Kimi K2.7 Code",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 42,
        "aa_rank": 38,
        "aa_official_coding_index": 57,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.95,
        "output_cost": 4,
        "tokens_per_second": 51,
        "latency": 2.82,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/kimi-k2-7-code",
        "canonical_family_name": "Kimi K2.7 Code",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Kimi K2.7 Code",
        "llmstats_source_model_id": "kimi-k2.7-code",
        "llmstats_source_model_url": "https://llm-stats.com/models/kimi-k2.7-code",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 32.2,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "kimi/kimi-linear-48b-a3b-instruct",
        "canonical_family_name": "Kimi Linear 48B A3B Instruct",
        "provider": "Kimi",
        "aa_representative_variant_id": "kimi/kimi-linear-48b-a3b-instruct:default",
        "aa_representative_name": "Kimi Linear 48B A3B Instruct",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 195,
        "aa_official_coding_index": 20,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-2-6b",
        "canonical_family_name": "LFM2 2.6B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-2-6b:default",
        "aa_representative_name": "LFM2 2.6B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 241,
        "aa_official_coding_index": 3,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-24b-a2b",
        "canonical_family_name": "LFM2 24B A2B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-24b-a2b:default",
        "aa_representative_name": "LFM2 24B A2B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 222,
        "aa_official_coding_index": 11,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-8b-a1b",
        "canonical_family_name": "LFM2 8B A1B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-8b-a1b:default",
        "aa_representative_name": "LFM2 8B A1B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 250,
        "aa_official_coding_index": 7,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-5-1-2b",
        "canonical_family_name": "LFM2.5-1.2B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-5-1-2b:thinking",
        "aa_representative_name": "LFM2.5-1.2B-Thinking",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 239,
        "aa_official_coding_index": 4,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-5-1-2b-instruct",
        "canonical_family_name": "LFM2.5-1.2B-Instruct",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-5-1-2b-instruct:default",
        "aa_representative_name": "LFM2.5-1.2B-Instruct",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 242,
        "aa_official_coding_index": 2,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-5-8b-a1b",
        "canonical_family_name": "LFM2.5-8B-A1B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-5-8b-a1b:default",
        "aa_representative_name": "LFM2.5-8B-A1B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 8,
        "aa_rank": 197,
        "aa_official_coding_index": 8,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 334,
        "latency": 2.15,
        "context_window": 32800,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "liquid-ai/lfm2-5-vl-1-6b",
        "canonical_family_name": "LFM2.5-VL-1.6B",
        "provider": "Liquid AI",
        "aa_representative_variant_id": "liquid-ai/lfm2-5-vl-1-6b:default",
        "aa_representative_name": "LFM2.5-VL-1.6B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 1,
        "aa_rank": 251,
        "aa_official_coding_index": 3,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 369,
        "latency": 11.9,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inclusionai/ling-2-6-flash",
        "canonical_family_name": "Ling 2.6 Flash",
        "provider": "InclusionAI",
        "aa_representative_variant_id": "inclusionai/ling-2-6-flash:default",
        "aa_representative_name": "Ling 2.6 Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 154,
        "aa_official_coding_index": 25.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.3,
        "tokens_per_second": 168,
        "latency": 1.16,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inclusionai/ling-2-6-1t",
        "canonical_family_name": "Ling-2.6-1T",
        "provider": "InclusionAI",
        "aa_representative_variant_id": "inclusionai/ling-2-6-1t:default",
        "aa_representative_name": "Ling-2.6-1T",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 26,
        "aa_rank": 91,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 2.5,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inclusionai/ling-mini-2-0",
        "canonical_family_name": "Ling-mini-2.0",
        "provider": "InclusionAI",
        "aa_representative_variant_id": "inclusionai/ling-mini-2-0:default",
        "aa_representative_name": "Ling-mini-2.0",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 233,
        "aa_official_coding_index": 14,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-3-1-405b",
        "canonical_family_name": "Llama 3.1 405B",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-3-1-405b:default",
        "aa_representative_name": "Llama 3.1 405B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 196,
        "aa_official_coding_index": 30,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2.5,
        "output_cost": 10,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/llama-3-1-nemotron-70b",
        "canonical_family_name": "Llama 3.1 Nemotron 70B",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/llama-3-1-nemotron-70b:default",
        "aa_representative_name": "Llama 3.1 Nemotron 70B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 8,
        "aa_rank": 202,
        "aa_official_coding_index": 23,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.2,
        "output_cost": 1.2,
        "tokens_per_second": 82,
        "latency": 8.99,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-3-2-11b-vision",
        "canonical_family_name": "Llama 3.2 11B (Vision)",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-3-2-11b-vision:default",
        "aa_representative_name": "Llama 3.2 11B (Vision)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 234,
        "aa_official_coding_index": 11,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.36,
        "output_cost": 0.36,
        "tokens_per_second": 8,
        "latency": 2.59,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-3-2-90b-vision",
        "canonical_family_name": "Llama 3.2 90B (Vision)",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-3-2-90b-vision:default",
        "aa_representative_name": "Llama 3.2 90B (Vision)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 213,
        "aa_official_coding_index": 24,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2.04,
        "output_cost": 2.04,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-3-3-70b",
        "canonical_family_name": "Llama 3.3 70B",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-3-3-70b:default",
        "aa_representative_name": "Llama 3.3 70B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 181,
        "aa_official_coding_index": 15.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.59,
        "output_cost": 0.72,
        "tokens_per_second": 83,
        "latency": 1.69,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-4-maverick",
        "canonical_family_name": "Llama 4 Maverick",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-4-maverick:default",
        "aa_representative_name": "Llama 4 Maverick",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 150,
        "aa_official_coding_index": 20.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.27,
        "output_cost": 0.85,
        "tokens_per_second": 111,
        "latency": 0.92,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/llama-4-scout",
        "canonical_family_name": "Llama 4 Scout",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/llama-4-scout:default",
        "aa_representative_name": "Llama 4 Scout",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 10,
        "aa_rank": 175,
        "aa_official_coding_index": 10.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.18,
        "output_cost": 0.66,
        "tokens_per_second": 96,
        "latency": 0.77,
        "context_window": 10000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/llama-nemotron-super-49b-v1-5",
        "canonical_family_name": "Llama Nemotron Super 49B v1.5",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/llama-nemotron-super-49b-v1-5:reasoning",
        "aa_representative_name": "Llama Nemotron Super 49B v1.5 (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 12,
        "aa_rank": 162,
        "aa_official_coding_index": 35,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.4,
        "output_cost": 0.4,
        "tokens_per_second": 72,
        "latency": 6.9,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/llama-nemotron-ultra",
        "canonical_family_name": "Llama Nemotron Ultra",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/llama-nemotron-ultra:reasoning",
        "aa_representative_name": "Llama Nemotron Ultra (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 182,
        "aa_official_coding_index": 35,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.6,
        "output_cost": 1.8,
        "tokens_per_second": 53,
        "latency": 2.32,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "longcat/longcat-2-0",
        "canonical_family_name": "LongCat 2.0",
        "provider": "LongCat",
        "aa_representative_variant_id": "longcat/longcat-2-0:default",
        "aa_representative_name": "LongCat 2.0",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 33,
        "aa_rank": 68,
        "aa_official_coding_index": 42.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "longcat/longcat-flash-lite",
        "canonical_family_name": "LongCat Flash Lite",
        "provider": "LongCat",
        "aa_representative_variant_id": "longcat/longcat-flash-lite:default",
        "aa_representative_name": "LongCat Flash Lite",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 17,
        "aa_rank": 134,
        "aa_official_coding_index": 28,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/magistral-medium-1-2",
        "canonical_family_name": "Magistral Medium 1.2",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/magistral-medium-1-2:medium",
        "aa_representative_name": "Magistral Medium 1.2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 18,
        "aa_rank": 128,
        "aa_official_coding_index": 25.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 5,
        "tokens_per_second": 44,
        "latency": 1.72,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/magistral-small-1-2",
        "canonical_family_name": "Magistral Small 1.2",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/magistral-small-1-2:default",
        "aa_representative_name": "Magistral Small 1.2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 11,
        "aa_rank": 170,
        "aa_official_coding_index": 19.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.5,
        "output_cost": 1.5,
        "tokens_per_second": 89,
        "latency": 0.94,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inception/mercury-2",
        "canonical_family_name": "Mercury 2",
        "provider": "Inception",
        "aa_representative_variant_id": "inception/mercury-2:default",
        "aa_representative_name": "Mercury 2",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 21,
        "aa_rank": 111,
        "aa_official_coding_index": 33,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 0.75,
        "tokens_per_second": 902,
        "latency": 4.29,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "korea-telecom/mi-dm-k-2-5-pro",
        "canonical_family_name": "Mi:dm K 2.5 Pro",
        "provider": "Korea Telecom",
        "aa_representative_variant_id": "korea-telecom/mi-dm-k-2-5-pro:default",
        "aa_representative_name": "Mi:dm K 2.5 Pro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 16,
        "aa_rank": 139,
        "aa_official_coding_index": 33,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "korea-telecom/mi-dm-k-2-5-pro-preview",
        "canonical_family_name": "Mi:dm K 2.5 Pro Preview",
        "provider": "Korea Telecom",
        "aa_representative_variant_id": "korea-telecom/mi-dm-k-2-5-pro-preview:preview",
        "aa_representative_name": "Mi:dm K 2.5 Pro Preview",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": null,
        "aa_rank": 261,
        "aa_official_coding_index": 30,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-flash",
        "canonical_family_name": "MiMo-V2-Flash",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-flash:default",
        "aa_representative_name": "MiMo-V2-Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 25,
        "aa_rank": 99,
        "aa_official_coding_index": 44,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-flash-feb-2026",
        "canonical_family_name": "MiMo-V2-Flash (Feb 2026)",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-flash-feb-2026:default",
        "aa_representative_name": "MiMo-V2-Flash (Feb 2026)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 33,
        "aa_rank": 70,
        "aa_official_coding_index": 38,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-omni",
        "canonical_family_name": "MiMo-V2-Omni",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-omni:default",
        "aa_representative_name": "MiMo-V2-Omni",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 35,
        "aa_rank": 59,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-omni-0327",
        "canonical_family_name": "MiMo-V2-Omni-0327",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-omni-0327:default",
        "aa_representative_name": "MiMo-V2-Omni-0327",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 36,
        "aa_rank": 56,
        "aa_official_coding_index": 39,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-5",
        "canonical_family_name": "MiMo-V2.5",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-5:default",
        "aa_representative_name": "MiMo-V2.5",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 37,
        "aa_rank": 53,
        "aa_official_coding_index": 53.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.14,
        "output_cost": 0.28,
        "tokens_per_second": 65,
        "latency": 3.57,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "xiaomi/mimo-v2-5-pro",
        "canonical_family_name": "MiMo-V2.5-Pro",
        "provider": "Xiaomi",
        "aa_representative_variant_id": "xiaomi/mimo-v2-5-pro:default",
        "aa_representative_name": "MiMo-V2.5-Pro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 42,
        "aa_rank": 37,
        "aa_official_coding_index": 57.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.43,
        "output_cost": 0.87,
        "tokens_per_second": 69,
        "latency": 2.88,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/mimo-v2-5-pro",
        "canonical_family_name": "MiMo-V2.5-Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "MiMo-V2.5-Pro",
        "llmstats_source_model_id": "mimo-v2.5-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/mimo-v2.5-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 32.2,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openbmb/minicpm-v-4-6-1-3b",
        "canonical_family_name": "MiniCPM-V 4.6 1.3B",
        "provider": "OpenBMB",
        "aa_representative_variant_id": "openbmb/minicpm-v-4-6-1-3b:default",
        "aa_representative_name": "MiniCPM-V 4.6 1.3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 228,
        "aa_official_coding_index": 1,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openbmb/minicpm5-1b",
        "canonical_family_name": "MiniCPM5-1B",
        "provider": "OpenBMB",
        "aa_representative_variant_id": "openbmb/minicpm5-1b:default",
        "aa_representative_name": "MiniCPM5-1B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 12,
        "aa_rank": 165,
        "aa_official_coding_index": 4,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/minimax-m3",
        "canonical_family_name": "MiniMax M3",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "MiniMax M3",
        "llmstats_source_model_id": "minimax-m3",
        "llmstats_source_model_url": "https://llm-stats.com/models/minimax-m3",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 35.4,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "minimax/minimax-m3",
        "canonical_family_name": "MiniMax-M3",
        "provider": "MiniMax",
        "aa_representative_variant_id": "minimax/minimax-m3:default",
        "aa_representative_name": "MiniMax-M3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 44,
        "aa_rank": 30,
        "aa_official_coding_index": 55,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 1.2,
        "tokens_per_second": 76,
        "latency": 1.47,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/ministral-3-14b",
        "canonical_family_name": "Ministral 3 14B",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/ministral-3-14b:default",
        "aa_representative_name": "Ministral 3 14B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 11,
        "aa_rank": 172,
        "aa_official_coding_index": 17,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.2,
        "output_cost": 0.2,
        "tokens_per_second": 69,
        "latency": 0.89,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/ministral-3-3b",
        "canonical_family_name": "Ministral 3 3B",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/ministral-3-3b:default",
        "aa_representative_name": "Ministral 3 3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 210,
        "aa_official_coding_index": 7,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.1,
        "tokens_per_second": 259,
        "latency": 0.65,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/ministral-3-8b",
        "canonical_family_name": "Ministral 3 8B",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/ministral-3-8b:default",
        "aa_representative_name": "Ministral 3 8B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 187,
        "aa_official_coding_index": 12.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.15,
        "output_cost": 0.15,
        "tokens_per_second": 121,
        "latency": 0.72,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/mistral-large-3",
        "canonical_family_name": "Mistral Large 3",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/mistral-large-3:default",
        "aa_representative_name": "Mistral Large 3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 16,
        "aa_rank": 142,
        "aa_official_coding_index": 24,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.5,
        "output_cost": 1.5,
        "tokens_per_second": 49,
        "latency": 1.16,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/mistral-medium-3-5",
        "canonical_family_name": "Mistral Medium 3.5",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/mistral-medium-3-5:medium",
        "aa_representative_name": "Mistral Medium 3.5",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 30,
        "aa_rank": 80,
        "aa_official_coding_index": 45.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.5,
        "output_cost": 7.5,
        "tokens_per_second": 84,
        "latency": 2.17,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "mistral-ai/mistral-small-4",
        "canonical_family_name": "Mistral Small 4",
        "provider": "Mistral AI",
        "aa_representative_variant_id": "mistral-ai/mistral-small-4:default",
        "aa_representative_name": "Mistral Small 4",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 20,
        "aa_rank": 121,
        "aa_official_coding_index": 29.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.15,
        "output_cost": 0.6,
        "tokens_per_second": 160,
        "latency": 0.8,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/molmo-7b-d",
        "canonical_family_name": "Molmo 7B-D",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/molmo-7b-d:default",
        "aa_representative_name": "Molmo 7B-D",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 232,
        "aa_official_coding_index": 4,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 4100,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/molmo2-8b",
        "canonical_family_name": "Molmo2-8B",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/molmo2-8b:default",
        "aa_representative_name": "Molmo2-8B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 2,
        "aa_rank": 249,
        "aa_official_coding_index": 13,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 36900,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "motif-technologies/motif-3-beta",
        "canonical_family_name": "Motif 3 (Beta)",
        "provider": "Motif Technologies",
        "aa_representative_variant_id": "motif-technologies/motif-3-beta:default",
        "aa_representative_name": "Motif 3 (Beta)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 44,
        "aa_rank": 33,
        "aa_official_coding_index": 57.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "motif-technologies/motif-2-12-7b",
        "canonical_family_name": "Motif-2-12.7B",
        "provider": "Motif Technologies",
        "aa_representative_variant_id": "motif-technologies/motif-2-12-7b:default",
        "aa_representative_name": "Motif-2-12.7B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 13,
        "aa_rank": 159,
        "aa_official_coding_index": 28,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/muse-spark-1-1",
        "canonical_family_name": "Muse Spark 1.1",
        "provider": "Meta",
        "aa_representative_variant_id": "meta/muse-spark-1-1:xhigh",
        "aa_representative_name": "Muse Spark 1.1 (xhigh)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 51,
        "aa_rank": 18,
        "aa_official_coding_index": 68,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.25,
        "output_cost": 4.25,
        "tokens_per_second": 117,
        "latency": 1.47,
        "context_window": 1050000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/muse-spark-1-1",
        "canonical_family_name": "Muse Spark 1.1",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Muse Spark 1.1",
        "llmstats_source_model_id": "muse-spark-1.1",
        "llmstats_source_model_url": "https://llm-stats.com/models/muse-spark-1.1",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 38.3,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "identity_unresolved",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nanbeige/nanbeige4-1-3b",
        "canonical_family_name": "Nanbeige4.1-3B",
        "provider": "Nanbeige",
        "aa_representative_variant_id": "nanbeige/nanbeige4-1-3b:default",
        "aa_representative_name": "Nanbeige4.1-3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 11,
        "aa_rank": 171,
        "aa_official_coding_index": 14,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
        "canonical_family_name": "Nemotron 3 Nano Omni 30B A3B Reasoning",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:reasoning",
        "aa_representative_name": "Nemotron 3 Nano Omni 30B A3B Reasoning",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 15,
        "aa_rank": 145,
        "aa_official_coding_index": 17.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.07,
        "output_cost": 0.3,
        "tokens_per_second": 314,
        "latency": 0.97,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nemotron-3-ultra",
        "canonical_family_name": "Nemotron 3 Ultra",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nemotron-3-ultra:default",
        "aa_representative_name": "Nemotron 3 Ultra",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 38,
        "aa_rank": 51,
        "aa_official_coding_index": 47,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.68,
        "output_cost": 2.67,
        "tokens_per_second": 182,
        "latency": 1.2,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nemotron-cascade-2-30b-a3b",
        "canonical_family_name": "Nemotron Cascade 2 30B A3B",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nemotron-cascade-2-30b-a3b:default",
        "aa_representative_name": "Nemotron Cascade 2 30B A3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 18,
        "aa_rank": 131,
        "aa_official_coding_index": 28,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nex-agi/nex-n2-pro",
        "canonical_family_name": "Nex-N2-Pro",
        "provider": "Nex AGI",
        "aa_representative_variant_id": "nex-agi/nex-n2-pro:default",
        "aa_representative_name": "Nex-N2-Pro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 41,
        "aa_rank": 42,
        "aa_official_coding_index": 55,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.5,
        "output_cost": 2.5,
        "tokens_per_second": 136,
        "latency": 1.76,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "cohere/north-mini-code",
        "canonical_family_name": "North Mini Code",
        "provider": "Cohere",
        "aa_representative_variant_id": "cohere/north-mini-code:default",
        "aa_representative_name": "North Mini Code",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 20,
        "aa_rank": 119,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 67,
        "latency": 0.58,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "amazon/nova-2-0-lite",
        "canonical_family_name": "Nova 2.0 Lite",
        "provider": "Amazon",
        "aa_representative_variant_id": "amazon/nova-2-0-lite:medium",
        "aa_representative_name": "Nova 2.0 Lite (medium)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 19,
        "aa_rank": 123,
        "aa_official_coding_index": 37,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 2.5,
        "tokens_per_second": 153,
        "latency": 19.37,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "amazon/nova-2-0-omni",
        "canonical_family_name": "Nova 2.0 Omni",
        "provider": "Amazon",
        "aa_representative_variant_id": "amazon/nova-2-0-omni:medium",
        "aa_representative_name": "Nova 2.0 Omni (medium)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 21,
        "aa_rank": 113,
        "aa_official_coding_index": 36,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 2.5,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "amazon/nova-2-0-pro-preview",
        "canonical_family_name": "Nova 2.0 Pro Preview",
        "provider": "Amazon",
        "aa_representative_variant_id": "amazon/nova-2-0-pro-preview:medium-preview",
        "aa_representative_name": "Nova 2.0 Pro Preview (medium)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 22,
        "aa_rank": 109,
        "aa_official_coding_index": 36.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 1.25,
        "output_cost": 10,
        "tokens_per_second": 115,
        "latency": 15.13,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "amazon/nova-micro",
        "canonical_family_name": "Nova Micro",
        "provider": "Amazon",
        "aa_representative_variant_id": "amazon/nova-micro:default",
        "aa_representative_name": "Nova Micro",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 224,
        "aa_official_coding_index": 9,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.04,
        "output_cost": 0.14,
        "tokens_per_second": 298,
        "latency": 0.9,
        "context_window": 130000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "amazon/nova-premier",
        "canonical_family_name": "Nova Premier",
        "provider": "Amazon",
        "aa_representative_variant_id": "amazon/nova-premier:default",
        "aa_representative_name": "Nova Premier",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 13,
        "aa_rank": 160,
        "aa_official_coding_index": 28,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2.5,
        "output_cost": 12.5,
        "tokens_per_second": 32,
        "latency": 2.88,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nvidia-nemotron-3-nano",
        "canonical_family_name": "NVIDIA Nemotron 3 Nano",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nvidia-nemotron-3-nano:reasoning",
        "aa_representative_name": "NVIDIA Nemotron 3 Nano (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 152,
        "aa_official_coding_index": 18.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.05,
        "output_cost": 0.2,
        "tokens_per_second": 117,
        "latency": 1.4,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nvidia-nemotron-3-nano-4b",
        "canonical_family_name": "NVIDIA Nemotron 3 Nano 4B",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nvidia-nemotron-3-nano-4b:default",
        "aa_representative_name": "NVIDIA Nemotron 3 Nano 4B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 192,
        "aa_official_coding_index": 10,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nvidia-nemotron-3-super",
        "canonical_family_name": "NVIDIA Nemotron 3 Super",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nvidia-nemotron-3-super:default",
        "aa_representative_name": "NVIDIA Nemotron 3 Super",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 25,
        "aa_rank": 96,
        "aa_official_coding_index": 37.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 0.78,
        "tokens_per_second": 249,
        "latency": 1.4,
        "context_window": 1000000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl",
        "canonical_family_name": "NVIDIA Nemotron Nano 12B v2 VL",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nvidia-nemotron-nano-12b-v2-vl:reasoning",
        "aa_representative_name": "NVIDIA Nemotron Nano 12B v2 VL (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 186,
        "aa_official_coding_index": 26,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.2,
        "output_cost": 0.6,
        "tokens_per_second": 65,
        "latency": 5.53,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "nvidia/nvidia-nemotron-nano-9b-v2",
        "canonical_family_name": "NVIDIA Nemotron Nano 9B V2",
        "provider": "NVIDIA",
        "aa_representative_variant_id": "nvidia/nvidia-nemotron-nano-9b-v2:reasoning",
        "aa_representative_name": "NVIDIA Nemotron Nano 9B V2 (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 190,
        "aa_official_coding_index": 22,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.04,
        "output_cost": 0.16,
        "tokens_per_second": 86,
        "latency": 7.34,
        "context_window": 131000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/o3",
        "canonical_family_name": "o3",
        "provider": "OpenAI",
        "aa_representative_variant_id": "openai/o3:default",
        "aa_representative_name": "o3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 30,
        "aa_rank": 78,
        "aa_official_coding_index": 41,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 2,
        "output_cost": 8,
        "tokens_per_second": 138,
        "latency": 5.73,
        "context_window": 200000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/olmo-3-7b",
        "canonical_family_name": "Olmo 3 7B",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/olmo-3-7b:default",
        "aa_representative_name": "Olmo 3 7B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 3,
        "aa_rank": 237,
        "aa_official_coding_index": 10,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.2,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/olmo-3-7b-think",
        "canonical_family_name": "Olmo 3 7B Think",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/olmo-3-7b-think:default",
        "aa_representative_name": "Olmo 3 7B Think",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 231,
        "aa_official_coding_index": 21,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/olmo-3-1-32b-instruct",
        "canonical_family_name": "Olmo 3.1 32B Instruct",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/olmo-3-1-32b-instruct:default",
        "aa_representative_name": "Olmo 3.1 32B Instruct",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 209,
        "aa_official_coding_index": 17,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "allen-institute-for-ai/olmo-3-1-32b-think",
        "canonical_family_name": "Olmo 3.1 32B Think",
        "provider": "Allen Institute for AI",
        "aa_representative_variant_id": "allen-institute-for-ai/olmo-3-1-32b-think:default",
        "aa_representative_name": "Olmo 3.1 32B Think",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 8,
        "aa_rank": 199,
        "aa_official_coding_index": 29,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "microsoft/phi-4",
        "canonical_family_name": "Phi-4",
        "provider": "Microsoft",
        "aa_representative_variant_id": "microsoft/phi-4:default",
        "aa_representative_name": "Phi-4",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 223,
        "aa_official_coding_index": 26,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.13,
        "output_cost": 0.5,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 16000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "microsoft/phi-4-mini",
        "canonical_family_name": "Phi-4 Mini",
        "provider": "Microsoft",
        "aa_representative_variant_id": "microsoft/phi-4-mini:default",
        "aa_representative_name": "Phi-4 Mini",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 214,
        "aa_official_coding_index": 5.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 44,
        "latency": 0.82,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "microsoft/phi-4-multimodal",
        "canonical_family_name": "Phi-4 Multimodal",
        "provider": "Microsoft",
        "aa_representative_variant_id": "microsoft/phi-4-multimodal:default",
        "aa_representative_name": "Phi-4 Multimodal",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 5,
        "aa_rank": 227,
        "aa_official_coding_index": 11,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": 18,
        "latency": 0.85,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-coder-next",
        "canonical_family_name": "Qwen3 Coder Next",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-coder-next:default",
        "aa_representative_name": "Qwen3 Coder Next",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 21,
        "aa_rank": 112,
        "aa_official_coding_index": 35,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.35,
        "output_cost": 1.2,
        "tokens_per_second": 123,
        "latency": 1.38,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-next-80b-a3b",
        "canonical_family_name": "Qwen3 Next 80B A3B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-next-80b-a3b:reasoning",
        "aa_representative_name": "Qwen3 Next 80B A3B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 17,
        "aa_rank": 137,
        "aa_official_coding_index": 23,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.5,
        "output_cost": 6,
        "tokens_per_second": 191,
        "latency": 2.21,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-omni-30b-a3b",
        "canonical_family_name": "Qwen3 Omni 30B A3B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-omni-30b-a3b:reasoning",
        "aa_representative_name": "Qwen3 Omni 30B A3B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 10,
        "aa_rank": 178,
        "aa_official_coding_index": 31,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 0.97,
        "tokens_per_second": 95,
        "latency": 1.94,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-0-8b",
        "canonical_family_name": "Qwen3.5 0.8B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-0-8b:default",
        "aa_representative_name": "Qwen3.5 0.8B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 217,
        "aa_official_coding_index": 0,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-122b-a10b",
        "canonical_family_name": "Qwen3.5 122B A10B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-122b-a10b:default",
        "aa_representative_name": "Qwen3.5 122B A10B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 32,
        "aa_rank": 71,
        "aa_official_coding_index": 45,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.4,
        "output_cost": 3.2,
        "tokens_per_second": 133,
        "latency": 2.35,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-2b",
        "canonical_family_name": "Qwen3.5 2B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-2b:default",
        "aa_representative_name": "Qwen3.5 2B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 7,
        "aa_rank": 206,
        "aa_official_coding_index": 3,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-35b-a3b",
        "canonical_family_name": "Qwen3.5 35B A3B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-35b-a3b:non-reasoning",
        "aa_representative_name": "Qwen3.5 35B A3B (non-reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 24,
        "aa_rank": 101,
        "aa_official_coding_index": 35,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 2,
        "tokens_per_second": 122,
        "latency": 2.18,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-4b",
        "canonical_family_name": "Qwen3.5 4B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-4b:default",
        "aa_representative_name": "Qwen3.5 4B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 20,
        "aa_rank": 118,
        "aa_official_coding_index": 21,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.03,
        "output_cost": 0.15,
        "tokens_per_second": 41,
        "latency": 0.81,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-9b",
        "canonical_family_name": "Qwen3.5 9B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-9b:default",
        "aa_representative_name": "Qwen3.5 9B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 21,
        "aa_rank": 110,
        "aa_official_coding_index": 28.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.14,
        "output_cost": 0.2,
        "tokens_per_second": 61,
        "latency": 1.83,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-omni-flash",
        "canonical_family_name": "Qwen3.5 Omni Flash",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-omni-flash:default",
        "aa_representative_name": "Qwen3.5 Omni Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 19,
        "aa_rank": 124,
        "aa_official_coding_index": 25,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.8,
        "tokens_per_second": 242,
        "latency": 1.84,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-omni-plus",
        "canonical_family_name": "Qwen3.5 Omni Plus",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-5-omni-plus:default",
        "aa_representative_name": "Qwen3.5 Omni Plus",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 31,
        "aa_rank": 75,
        "aa_official_coding_index": 41,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.4,
        "output_cost": 4.8,
        "tokens_per_second": 49,
        "latency": 2.39,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-6-27b",
        "canonical_family_name": "Qwen3.6 27B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-6-27b:default",
        "aa_representative_name": "Qwen3.6 27B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 37,
        "aa_rank": 54,
        "aa_official_coding_index": 50.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.6,
        "output_cost": 3.6,
        "tokens_per_second": 56,
        "latency": 3.7,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-6-35b-a3b",
        "canonical_family_name": "Qwen3.6 35B A3B",
        "provider": "Alibaba",
        "aa_representative_variant_id": "alibaba/qwen3-6-35b-a3b:default",
        "aa_representative_name": "Qwen3.6 35B A3B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 32,
        "aa_rank": 73,
        "aa_official_coding_index": 40.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "identity_review",
        "score_status_label": "Identity review",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.25,
        "output_cost": 1.49,
        "tokens_per_second": 158,
        "latency": 2.21,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "review",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "perplexity/r1-1776",
        "canonical_family_name": "R1 1776",
        "provider": "Perplexity",
        "aa_representative_variant_id": "perplexity/r1-1776:default",
        "aa_representative_name": "R1 1776",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 6,
        "aa_rank": 212,
        "aa_official_coding_index": null,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "reka-ai/reka-flash-3",
        "canonical_family_name": "Reka Flash 3",
        "provider": "Reka AI",
        "aa_representative_variant_id": "reka-ai/reka-flash-3:default",
        "aa_representative_name": "Reka Flash 3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 4,
        "aa_rank": 230,
        "aa_official_coding_index": 27,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.2,
        "output_cost": 0.8,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inclusionai/ring-2-6-1t",
        "canonical_family_name": "Ring-2.6-1T",
        "provider": "InclusionAI",
        "aa_representative_variant_id": "inclusionai/ring-2-6-1t:default",
        "aa_representative_name": "Ring-2.6-1T",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 31,
        "aa_rank": 76,
        "aa_official_coding_index": 42.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.3,
        "output_cost": 2.5,
        "tokens_per_second": 121,
        "latency": 3.31,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "inclusionai/ring-flash-2-0",
        "canonical_family_name": "Ring-flash-2.0",
        "provider": "InclusionAI",
        "aa_representative_variant_id": "inclusionai/ring-flash-2-0:default",
        "aa_representative_name": "Ring-flash-2.0",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 8,
        "aa_rank": 198,
        "aa_official_coding_index": 17,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.14,
        "output_cost": 0.57,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "sarvam/sarvam-105b",
        "canonical_family_name": "Sarvam 105B",
        "provider": "Sarvam",
        "aa_representative_variant_id": "sarvam/sarvam-105b:high",
        "aa_representative_name": "Sarvam 105B (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 12,
        "aa_rank": 166,
        "aa_official_coding_index": 26,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.04,
        "output_cost": 0.17,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "sarvam/sarvam-30b",
        "canonical_family_name": "Sarvam 30B",
        "provider": "Sarvam",
        "aa_representative_variant_id": "sarvam/sarvam-30b:high",
        "aa_representative_name": "Sarvam 30B (high)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 7,
        "aa_rank": 208,
        "aa_official_coding_index": 19,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.03,
        "output_cost": 0.11,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "bytedance/seed-2-0-pro",
        "canonical_family_name": "Seed 2.0 Pro",
        "provider": "Bytedance",
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Seed 2.0 Pro",
        "llmstats_source_model_id": "seed-2.0-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/seed-2.0-pro",
        "llmstats_general_score": 40.3,
        "llmstats_general_rank": 24,
        "llmstats_coding_score": 21,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/seed-2-1-pro",
        "canonical_family_name": "Seed 2.1 Pro",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Seed 2.1 Pro",
        "llmstats_source_model_id": "seed-2.1-pro",
        "llmstats_source_model_url": "https://llm-stats.com/models/seed-2.1-pro",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 36.3,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "unknown/seed-2-1-turbo",
        "canonical_family_name": "Seed 2.1 Turbo",
        "provider": null,
        "aa_representative_variant_id": null,
        "aa_representative_name": null,
        "aa_intelligence": null,
        "aa_rank": null,
        "aa_official_coding_index": null,
        "llmstats_source_name": "Seed 2.1 Turbo",
        "llmstats_source_model_id": "seed-2.1-turbo",
        "llmstats_source_model_url": "https://llm-stats.com/models/seed-2.1-turbo",
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": 32.8,
        "score_status": "llmstats_only",
        "score_status_label": "LLMStats only",
        "availability_class": "unknown",
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "upstage/solar-open-100b",
        "canonical_family_name": "Solar Open 100B",
        "provider": "Upstage",
        "aa_representative_variant_id": "upstage/solar-open-100b:reasoning",
        "aa_representative_name": "Solar Open 100B (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 15,
        "aa_rank": 144,
        "aa_official_coding_index": 27,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "upstage/solar-pro-2",
        "canonical_family_name": "Solar Pro 2",
        "provider": "Upstage",
        "aa_representative_variant_id": "upstage/solar-pro-2:reasoning",
        "aa_representative_name": "Solar Pro 2 (reasoning)",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 185,
        "aa_official_coding_index": 30,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "upstage/solar-pro-3",
        "canonical_family_name": "Solar Pro 3",
        "provider": "Upstage",
        "aa_representative_variant_id": "upstage/solar-pro-3:default",
        "aa_representative_name": "Solar Pro 3",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 153,
        "aa_official_coding_index": 18.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 128000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "stepfun/step-3-5-flash-2603",
        "canonical_family_name": "Step 3.5 Flash 2603",
        "provider": "StepFun",
        "aa_representative_variant_id": "stepfun/step-3-5-flash-2603:default",
        "aa_representative_name": "Step 3.5 Flash 2603",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 26,
        "aa_rank": 92,
        "aa_official_coding_index": 39,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "proprietary",
        "license_name": "Proprietary",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.1,
        "output_cost": 0.3,
        "tokens_per_second": 291,
        "latency": 1.17,
        "context_window": 256000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "stepfun/step-3-7-flash",
        "canonical_family_name": "Step 3.7 Flash",
        "provider": "StepFun",
        "aa_representative_variant_id": "stepfun/step-3-7-flash:default",
        "aa_representative_name": "Step 3.7 Flash",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 30,
        "aa_rank": 79,
        "aa_official_coding_index": 39.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.2,
        "output_cost": 1.15,
        "tokens_per_second": 381,
        "latency": 0.88,
        "context_window": 262000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "stepfun/step3-vl-10b",
        "canonical_family_name": "Step3 VL 10B",
        "provider": "StepFun",
        "aa_representative_variant_id": "stepfun/step3-vl-10b:default",
        "aa_representative_name": "Step3 VL 10B",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 9,
        "aa_rank": 180,
        "aa_official_coding_index": 31,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 65500,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "cohere/tiny-aya-global",
        "canonical_family_name": "Tiny Aya Global",
        "provider": "Cohere",
        "aa_representative_variant_id": "cohere/tiny-aya-global:default",
        "aa_representative_name": "Tiny Aya Global",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 1,
        "aa_rank": 253,
        "aa_official_coding_index": 4,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0,
        "output_cost": 0,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 8189,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "trillion-labs/tri-21b-think",
        "canonical_family_name": "Tri-21B-Think",
        "provider": "Trillion Labs",
        "aa_representative_variant_id": "trillion-labs/tri-21b-think:default",
        "aa_representative_name": "Tri-21B-Think",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 12,
        "aa_rank": 164,
        "aa_official_coding_index": 17,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "trillion-labs/tri-21b-think-preview",
        "canonical_family_name": "Tri-21B-think Preview",
        "provider": "Trillion Labs",
        "aa_representative_variant_id": "trillion-labs/tri-21b-think-preview:preview",
        "aa_representative_name": "Tri-21B-think Preview",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 14,
        "aa_rank": 156,
        "aa_official_coding_index": 18,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": null,
        "output_cost": null,
        "tokens_per_second": null,
        "latency": null,
        "context_window": 32000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "arcee-ai/trinity-large",
        "canonical_family_name": "Trinity Large",
        "provider": "Arcee AI",
        "aa_representative_variant_id": "arcee-ai/trinity-large:thinking",
        "aa_representative_name": "Trinity Large Thinking",
        "representative_selection_method": "best_aa_performance_rank_then_intelligence_then_name",
        "representative_selected_at": "2026-07-26T07:06:51.533284+00:00",
        "aa_intelligence": 18,
        "aa_rank": 127,
        "aa_official_coding_index": 28.5,
        "llmstats_source_name": null,
        "llmstats_source_model_id": null,
        "llmstats_source_model_url": null,
        "llmstats_general_score": null,
        "llmstats_general_rank": null,
        "llmstats_coding_score": null,
        "score_status": "aa_only",
        "score_status_label": "AA only",
        "availability_class": "open_weights",
        "license_name": "Open",
        "weights_available": null,
        "source_code_available": null,
        "training_data_disclosed": null,
        "commercial_use_allowed": null,
        "input_cost": 0.23,
        "output_cost": 0.88,
        "tokens_per_second": 172,
        "latency": 0.88,
        "context_window": 512000,
        "source_coverage": 1,
        "mapping_status": "source_missing",
        "generated_at": "2026-07-26T07:06:51.533284+00:00",
        "llmdex_score": null,
        "llmdex_rank": null,
        "aa_percentile": null,
        "llmstats_percentile": null,
        "agreement": null,
        "agreement_label": null,
        "score_version": "LLMDEX General Consensus v1",
        "score_scope": "not_scored_missing_or_unapproved_source",
        "matched_population_size": 0,
        "coding_score_status": "unavailable",
        "is_sota": false,
        "is_open_sota": false
      }
    ],
    "consensus": [
      {
        "family_id": "openai/gpt-5-6-sol",
        "canonical_family_name": "GPT-5.6 Sol",
        "provider": "OpenAI",
        "representative_variant_id": "openai/gpt-5-6-sol:max",
        "representative_model_name": "GPT-5.6 Sol (max)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 59,
        "aa_rank": 4,
        "llmstats_general_score": 58,
        "llmstats_general_rank": 1,
        "llmdex_score": 100,
        "llmdex_rank": 1,
        "agreement": 100,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": true,
        "is_open_sota": false
      },
      {
        "family_id": "kimi/kimi-k3",
        "canonical_family_name": "Kimi K3",
        "provider": "Kimi",
        "representative_variant_id": "kimi/kimi-k3:default",
        "representative_model_name": "Kimi K3",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 57,
        "aa_rank": 7,
        "llmstats_general_score": 55.7,
        "llmstats_general_rank": 3,
        "llmdex_score": 93.33333333333333,
        "llmdex_rank": 2,
        "agreement": 100,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-opus-4-8",
        "canonical_family_name": "Claude Opus 4.8",
        "provider": "Anthropic",
        "representative_variant_id": "anthropic/claude-opus-4-8:max",
        "representative_model_name": "Claude Opus 4.8 (max)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 56,
        "aa_rank": 10,
        "llmstats_general_score": 52.6,
        "llmstats_general_rank": 5,
        "llmdex_score": 83.33333333333334,
        "llmdex_rank": 3.5,
        "agreement": 93.33333333333333,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-6-terra",
        "canonical_family_name": "GPT-5.6 Terra",
        "provider": "OpenAI",
        "representative_variant_id": "openai/gpt-5-6-terra:max",
        "representative_model_name": "GPT-5.6 Terra (max)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 55,
        "aa_rank": 11,
        "llmstats_general_score": 53.3,
        "llmstats_general_rank": 4,
        "llmdex_score": 83.33333333333334,
        "llmdex_rank": 3.5,
        "agreement": 93.33333333333333,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "openai/gpt-5-6-luna",
        "canonical_family_name": "GPT-5.6 Luna",
        "provider": "OpenAI",
        "representative_variant_id": "openai/gpt-5-6-luna:max",
        "representative_model_name": "GPT-5.6 Luna (max)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 51,
        "aa_rank": 16,
        "llmstats_general_score": 46.8,
        "llmstats_general_rank": 9,
        "llmdex_score": 73.33333333333333,
        "llmdex_rank": 5,
        "agreement": 100,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-7",
        "canonical_family_name": "Qwen3.7",
        "provider": "Alibaba",
        "representative_variant_id": "alibaba/qwen3-7:max",
        "representative_model_name": "Qwen3.7 Max",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 46,
        "aa_rank": 27,
        "llmstats_general_score": 46.7,
        "llmstats_general_rank": 10,
        "llmdex_score": 65,
        "llmdex_rank": 6,
        "agreement": 96.66666666666666,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "deepseek/deepseek-v4-pro",
        "canonical_family_name": "DeepSeek V4 Pro",
        "provider": "DeepSeek",
        "representative_variant_id": "deepseek/deepseek-v4-pro:max",
        "representative_model_name": "DeepSeek V4 Pro (max)",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "aa_intelligence": 44,
        "aa_rank": 31,
        "llmstats_general_score": 44,
        "llmstats_general_rank": 14,
        "llmdex_score": 53.333333333333336,
        "llmdex_rank": 7,
        "agreement": 100,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": true
      },
      {
        "family_id": "anthropic/claude-opus-4-7",
        "canonical_family_name": "Claude Opus 4.7",
        "provider": "Anthropic",
        "representative_variant_id": "anthropic/claude-opus-4-7:high-non-reasoning",
        "representative_model_name": "Claude Opus 4.7 (Non-reasoning, high)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 43,
        "aa_rank": 36,
        "llmstats_general_score": 45.6,
        "llmstats_general_rank": 12,
        "llmdex_score": 51.66666666666667,
        "llmdex_rank": 8,
        "agreement": 83.33333333333334,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "google/gemini-3-1-pro-preview",
        "canonical_family_name": "Gemini 3.1 Pro Preview",
        "provider": "Google",
        "representative_variant_id": "google/gemini-3-1-pro-preview:preview",
        "representative_model_name": "Gemini 3.1 Pro Preview",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 46,
        "aa_rank": 25,
        "llmstats_general_score": 43.6,
        "llmstats_general_rank": 18,
        "llmdex_score": 48.333333333333336,
        "llmdex_rank": 9,
        "agreement": 70,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "tencent/hy3",
        "canonical_family_name": "Hy3",
        "provider": "Tencent",
        "representative_variant_id": "tencent/hy3:default",
        "representative_model_name": "Hy3",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "aa_intelligence": 41,
        "aa_rank": 40,
        "llmstats_general_score": 43.8,
        "llmstats_general_rank": 15.5,
        "llmdex_score": 38.333333333333336,
        "llmdex_rank": 10,
        "agreement": 90,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "meta/muse-spark",
        "canonical_family_name": "Muse Spark",
        "provider": "Meta",
        "representative_variant_id": "meta/muse-spark:default",
        "representative_model_name": "Muse Spark",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 43,
        "aa_rank": 35,
        "llmstats_general_score": 42.5,
        "llmstats_general_rank": 20,
        "llmdex_score": 35,
        "llmdex_rank": 11,
        "agreement": 83.33333333333333,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-7-plus",
        "canonical_family_name": "Qwen3.7 Plus",
        "provider": "Alibaba",
        "representative_variant_id": "alibaba/qwen3-7-plus:default",
        "representative_model_name": "Qwen3.7 Plus",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 39,
        "aa_rank": 47,
        "llmstats_general_score": 43.8,
        "llmstats_general_rank": 15.5,
        "llmdex_score": 28.333333333333336,
        "llmdex_rank": 12,
        "agreement": 70,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-6-plus",
        "canonical_family_name": "Qwen3.6 Plus",
        "provider": "Alibaba",
        "representative_variant_id": "alibaba/qwen3-6-plus:default",
        "representative_model_name": "Qwen3.6 Plus",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 40,
        "aa_rank": 46,
        "llmstats_general_score": 40.4,
        "llmstats_general_rank": 23,
        "llmdex_score": 21.666666666666664,
        "llmdex_rank": 13,
        "agreement": 96.66666666666667,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "deepseek/deepseek-v4-flash",
        "canonical_family_name": "DeepSeek V4 Flash",
        "provider": "DeepSeek",
        "representative_variant_id": "deepseek/deepseek-v4-flash:max",
        "representative_model_name": "DeepSeek V4 Flash (max)",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "aa_intelligence": 40,
        "aa_rank": 45,
        "llmstats_general_score": 39.7,
        "llmstats_general_rank": 25,
        "llmdex_score": 18.333333333333332,
        "llmdex_rank": 14,
        "agreement": 90,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "alibaba/qwen3-5-397b-a17b",
        "canonical_family_name": "Qwen3.5 397B A17B",
        "provider": "Alibaba",
        "representative_variant_id": "alibaba/qwen3-5-397b-a17b:default",
        "representative_model_name": "Qwen3.5 397B A17B",
        "availability_class": "open_weights",
        "is_open_weights": true,
        "aa_intelligence": 34,
        "aa_rank": 66,
        "llmstats_general_score": 39.6,
        "llmstats_general_rank": 26,
        "llmdex_score": 5,
        "llmdex_rank": 15,
        "agreement": 96.66666666666667,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      },
      {
        "family_id": "anthropic/claude-sonnet-4-6",
        "canonical_family_name": "Claude Sonnet 4.6",
        "provider": "Anthropic",
        "representative_variant_id": "anthropic/claude-sonnet-4-6:low-non-reasoning",
        "representative_model_name": "Claude Sonnet 4.6 (Non-reasoning, Low Effort)",
        "availability_class": "proprietary",
        "is_open_weights": false,
        "aa_intelligence": 34,
        "aa_rank": 62,
        "llmstats_general_score": 38.4,
        "llmstats_general_rank": 28,
        "llmdex_score": 1.6666666666666667,
        "llmdex_rank": 16,
        "agreement": 96.66666666666667,
        "source_coverage": null,
        "score_status": "consensus",
        "score_version": "LLMDEX General Consensus v1",
        "is_sota": false,
        "is_open_sota": false
      }
    ],
    "quality": {
      "generated_at": "2026-07-26T07:06:51.533284+00:00",
      "methodology_version": "LLMDEX General Consensus v1",
      "status": "healthy",
      "sources": {
        "artificial_analysis": {
          "source": "Artificial Analysis",
          "status": "healthy",
          "rows_scraped": 264,
          "expected_range": [
            150,
            500
          ],
          "duration_seconds": 0,
          "warnings": [
            "Health synthesized from the current validated publication."
          ],
          "last_successful_update": "2026-07-26T07:06:51.533284+00:00",
          "schema_changes": [],
          "error_message": null,
          "timestamp": "2026-07-26T07:06:51.533284+00:00",
          "snapshot_age_hours": 0
        },
        "llmstats": {
          "source": "LLMStats",
          "rows_scraped": 85,
          "expected_range": [
            20,
            250
          ],
          "status": "healthy",
          "error_message": null,
          "duration_seconds": 20.1,
          "timestamp": "2026-07-26T07:07:11.639936+00:00",
          "parse_warning_count": 0,
          "warnings": [],
          "last_successful_update": "2026-07-26T07:07:11.639936+00:00",
          "schema_changes": [],
          "snapshot_age_hours": 0
        }
      },
      "counts": {
        "matched_families": 16,
        "aa_only_families": 145,
        "llmstats_only_families": 26,
        "identity_review_count": 69,
        "ambiguous_match_count": 9,
        "consensus_scored_families": 16
      },
      "missing_benchmark_counts": {
        "aa_intelligence": 72,
        "llmstats_general": 226,
        "aa_official_coding_index": 71,
        "llmstats_coding": 215
      },
      "warnings": []
    },
    "methodology": {
      "generated_at": "2026-07-26T07:06:51.533284+00:00",
      "methodology_version": "LLMDEX General Consensus v1",
      "source_updated_at": {
        "artificial_analysis": "2026-07-26T07:06:51.533284+00:00",
        "llmstats": "2026-07-26T07:07:11.639936+00:00"
      },
      "source_health": {
        "artificial_analysis": {
          "source": "Artificial Analysis",
          "status": "healthy",
          "rows_scraped": 264,
          "expected_range": [
            150,
            500
          ],
          "duration_seconds": 0,
          "warnings": [
            "Health synthesized from the current validated publication."
          ],
          "last_successful_update": "2026-07-26T07:06:51.533284+00:00",
          "schema_changes": [],
          "error_message": null,
          "timestamp": "2026-07-26T07:06:51.533284+00:00"
        },
        "llmstats": {
          "source": "LLMStats",
          "rows_scraped": 85,
          "expected_range": [
            20,
            250
          ],
          "status": "healthy",
          "error_message": null,
          "duration_seconds": 20.1,
          "timestamp": "2026-07-26T07:07:11.639936+00:00",
          "parse_warning_count": 0,
          "warnings": [],
          "last_successful_update": "2026-07-26T07:07:11.639936+00:00",
          "schema_changes": []
        }
      },
      "attribution": {
        "general": "General intelligence, pricing and API performance data from Artificial Analysis.",
        "capabilities": "Capability rankings and benchmark data from LLMStats."
      },
      "contracts": {
        "general": "data/index/latest.json",
        "families": "data/families/latest.json",
        "capabilities": "data/capabilities/latest.json",
        "quality": "data/quality/latest.json",
        "identity_audit": "data/identity/match_audit.csv"
      }
    }
  }
}