{
  "benchmarks": {
    "adversarial_nli": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 15,
      "score_col": "Score",
      "source_rows": 19,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "aider_polyglot": {
      "cost_rows": 67,
      "dated_rows": 61,
      "metrics_rows": 61,
      "parsed_rows": 72,
      "score_col": "Percent correct",
      "source_rows": 77,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "ale_bench": {
      "cost_rows": 132,
      "dated_rows": 0,
      "metrics_rows": 132,
      "parsed_rows": 132,
      "score_col": "Performance",
      "source_rows": 132,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "algotune": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 18,
      "score_col": "Score",
      "source_rows": 18,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "apex_agents": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 60,
      "score_col": "Pass@1 score",
      "source_rows": 60,
      "trace_rows": 0,
      "uncertainty_rows": 60
    },
    "arc_agi": {
      "cost_rows": 159,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 309,
      "score_col": "Score",
      "source_rows": 312,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "arc_agi_2": {
      "cost_rows": 151,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 290,
      "score_col": "Score",
      "source_rows": 290,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "arc_ai2": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 134,
      "score_col": "Challenge score",
      "source_rows": 145,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "balrog": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 41,
      "score_col": "Average progress",
      "source_rows": 41,
      "trace_rows": 14,
      "uncertainty_rows": 41
    },
    "bbh": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 88,
      "score_col": "Average",
      "source_rows": 92,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "blueprint_bench_2": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 35,
      "score_col": "Score",
      "source_rows": 35,
      "trace_rows": 0,
      "uncertainty_rows": 35
    },
    "bool_q": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 136,
      "score_col": "Score",
      "source_rows": 206,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "btf3": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 15,
      "score_col": "Pooled score",
      "source_rows": 15,
      "trace_rows": 0,
      "uncertainty_rows": 15
    },
    "cad_eval": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 15,
      "score_col": "Overall pass (%)",
      "source_rows": 15,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "chess_puzzles": {
      "cost_rows": 0,
      "dated_rows": 162,
      "metrics_rows": 0,
      "parsed_rows": 162,
      "score_col": "mean_score",
      "source_rows": 162,
      "trace_rows": 162,
      "uncertainty_rows": 162
    },
    "cl_bench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 23,
      "score_col": "Overall",
      "source_rows": 23,
      "trace_rows": 0,
      "uncertainty_rows": 23
    },
    "cl_bench_life": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 17,
      "score_col": "Overall",
      "source_rows": 17,
      "trace_rows": 0,
      "uncertainty_rows": 17
    },
    "common_sense_qa_2": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 6,
      "score_col": "Score",
      "source_rows": 10,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "critpt": {
      "cost_rows": 11,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 260,
      "score_col": "Accuracy",
      "source_rows": 260,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "cursorbench": {
      "cost_rows": 82,
      "dated_rows": 0,
      "metrics_rows": 82,
      "parsed_rows": 82,
      "score_col": "Score",
      "source_rows": 82,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "cybench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 22,
      "score_col": "Unguided % Solved",
      "source_rows": 22,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "deepresearchbench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 41,
      "score_col": "Average score",
      "source_rows": 41,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "deepswe": {
      "cost_rows": 69,
      "dated_rows": 0,
      "metrics_rows": 69,
      "parsed_rows": 69,
      "score_col": "Pass@1",
      "source_rows": 69,
      "trace_rows": 0,
      "uncertainty_rows": 69
    },
    "enigma_eval": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 46,
      "score_col": "Accuracy",
      "source_rows": 46,
      "trace_rows": 0,
      "uncertainty_rows": 46
    },
    "exploitbench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 20,
      "parsed_rows": 20,
      "score_col": "Mean capability",
      "source_rows": 20,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "fictionlivebench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 42,
      "score_col": "120k token score",
      "source_rows": 62,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "forecastbench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 92,
      "score_col": "Overall score",
      "source_rows": 92,
      "trace_rows": 0,
      "uncertainty_rows": 92
    },
    "frontiercode": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 46,
      "score_col": "Main score",
      "source_rows": 51,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "frontiermath": {
      "cost_rows": 0,
      "dated_rows": 100,
      "metrics_rows": 0,
      "parsed_rows": 101,
      "score_col": "mean_score",
      "source_rows": 101,
      "trace_rows": 79,
      "uncertainty_rows": 101
    },
    "frontiermath_tier_4": {
      "cost_rows": 0,
      "dated_rows": 71,
      "metrics_rows": 0,
      "parsed_rows": 72,
      "score_col": "mean_score",
      "source_rows": 72,
      "trace_rows": 46,
      "uncertainty_rows": 72
    },
    "gbaeval": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 23,
      "parsed_rows": 23,
      "score_col": "Overall score",
      "source_rows": 23,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "gdp_pdf": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 56,
      "score_col": "GDP.pdf score",
      "source_rows": 59,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "gdpval": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 11,
      "score_col": "Win Rate (%)",
      "source_rows": 11,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "geobench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 32,
      "score_col": "ACW Avg Score",
      "source_rows": 32,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "gpqa_diamond": {
      "cost_rows": 0,
      "dated_rows": 333,
      "metrics_rows": 0,
      "parsed_rows": 334,
      "score_col": "mean_score",
      "source_rows": 334,
      "trace_rows": 331,
      "uncertainty_rows": 334
    },
    "gsm8k": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 170,
      "score_col": "EM",
      "source_rows": 235,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "gso": {
      "cost_rows": 0,
      "dated_rows": 36,
      "metrics_rows": 0,
      "parsed_rows": 42,
      "score_col": "Score OPT@1",
      "source_rows": 42,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "hella_swag": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 113,
      "score_col": "Overall accuracy",
      "source_rows": 135,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "hle": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 54,
      "parsed_rows": 56,
      "score_col": "Accuracy",
      "source_rows": 56,
      "trace_rows": 0,
      "uncertainty_rows": 56
    },
    "lambada": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 53,
      "score_col": "Score",
      "source_rows": 80,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "lech_mazur_writing": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 49,
      "score_col": "Mean score",
      "source_rows": 49,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "live_bench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 54,
      "score_col": "Global average",
      "source_rows": 64,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "math_level_5": {
      "cost_rows": 0,
      "dated_rows": 108,
      "metrics_rows": 0,
      "parsed_rows": 108,
      "score_col": "mean_score",
      "source_rows": 108,
      "trace_rows": 108,
      "uncertainty_rows": 108
    },
    "metr_time_horizons": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 49,
      "score_col": "Time horizon",
      "source_rows": 49,
      "trace_rows": 0,
      "uncertainty_rows": 49
    },
    "mindcube": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 5,
      "score_col": "Overall score",
      "source_rows": 5,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "mmlu": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 217,
      "score_col": "EM",
      "source_rows": 249,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "mystery_game_puzzles": {
      "cost_rows": 0,
      "dated_rows": 144,
      "metrics_rows": 0,
      "parsed_rows": 144,
      "score_col": "mean_score",
      "source_rows": 144,
      "trace_rows": 92,
      "uncertainty_rows": 144
    },
    "open_book_qa": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 70,
      "score_col": "Accuracy",
      "source_rows": 71,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "os_world": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 20,
      "score_col": "Score",
      "source_rows": 58,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "osworld_2": {
      "cost_rows": 7,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 16,
      "score_col": "Binary accuracy",
      "source_rows": 16,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "otis_mock_aime_2024_2025": {
      "cost_rows": 0,
      "dated_rows": 313,
      "metrics_rows": 0,
      "parsed_rows": 314,
      "score_col": "mean_score",
      "source_rows": 314,
      "trace_rows": 312,
      "uncertainty_rows": 314
    },
    "piqa": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 113,
      "score_col": "Score",
      "source_rows": 140,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "posttrainbench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 12,
      "score_col": "Average (%)",
      "source_rows": 12,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "proofbench": {
      "cost_rows": 82,
      "dated_rows": 0,
      "metrics_rows": 84,
      "parsed_rows": 84,
      "score_col": "Accuracy",
      "source_rows": 84,
      "trace_rows": 0,
      "uncertainty_rows": 57
    },
    "rli": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 18,
      "score_col": "Score",
      "source_rows": 18,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "scicode": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 235,
      "score_col": "Score",
      "source_rows": 235,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "science_qa": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 26,
      "score_col": "Score",
      "source_rows": 104,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "simplebench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 102,
      "score_col": "Score (AVG@5)",
      "source_rows": 104,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "simpleqa_verified": {
      "cost_rows": 0,
      "dated_rows": 101,
      "metrics_rows": 0,
      "parsed_rows": 101,
      "score_col": "mean_score",
      "source_rows": 101,
      "trace_rows": 89,
      "uncertainty_rows": 101
    },
    "spatialviz_bench": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 8,
      "score_col": "Overall score",
      "source_rows": 8,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "superglue": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 10,
      "score_col": "Score",
      "source_rows": 11,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "surface_evolver_bench": {
      "cost_rows": 29,
      "dated_rows": 0,
      "metrics_rows": 29,
      "parsed_rows": 29,
      "score_col": "Mean score",
      "source_rows": 29,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "swe_bench_verified": {
      "cost_rows": 0,
      "dated_rows": 35,
      "metrics_rows": 0,
      "parsed_rows": 35,
      "score_col": "mean_score",
      "source_rows": 35,
      "trace_rows": 34,
      "uncertainty_rows": 35
    },
    "terminalbench": {
      "cost_rows": 0,
      "dated_rows": 202,
      "metrics_rows": 0,
      "parsed_rows": 202,
      "score_col": "Accuracy mean",
      "source_rows": 204,
      "trace_rows": 0,
      "uncertainty_rows": 193
    },
    "the_agent_company": {
      "cost_rows": 15,
      "dated_rows": 0,
      "metrics_rows": 15,
      "parsed_rows": 16,
      "score_col": "% Score",
      "source_rows": 16,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "trivia_qa": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 115,
      "score_col": "EM",
      "source_rows": 115,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "vending_bench_2": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 71,
      "score_col": "Score",
      "source_rows": 71,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "video_mme": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 50,
      "score_col": "Overall (no subtitles)",
      "source_rows": 50,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "vpct": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 38,
      "score_col": "Correct",
      "source_rows": 38,
      "trace_rows": 0,
      "uncertainty_rows": 0
    },
    "webdev_arena": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 135,
      "parsed_rows": 135,
      "score_col": "Arena Score",
      "source_rows": 141,
      "trace_rows": 0,
      "uncertainty_rows": 135
    },
    "weirdml": {
      "cost_rows": 173,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 173,
      "score_col": "Accuracy",
      "source_rows": 174,
      "trace_rows": 0,
      "uncertainty_rows": 158
    },
    "wino_grande": {
      "cost_rows": 0,
      "dated_rows": 0,
      "metrics_rows": 0,
      "parsed_rows": 137,
      "score_col": "Accuracy",
      "source_rows": 145,
      "trace_rows": 0,
      "uncertainty_rows": 0
    }
  },
  "counts": {
    "benchmarks": 72,
    "invalid_dates": 0,
    "metadata_conflicts": 1,
    "models": 668,
    "openrouter_collisions": 0,
    "quarantined": 18,
    "scores": 6107
  },
  "coverage": {
    "context": {
      "percent": 51.9,
      "rows": 3172,
      "total": 6107
    },
    "cost": {
      "percent": 16,
      "rows": 977,
      "total": 6107
    },
    "eval_date": {
      "percent": 27.3,
      "rows": 1666,
      "total": 6107
    },
    "flop": {
      "percent": 34.6,
      "rows": 2112,
      "total": 6107
    },
    "metrics": {
      "percent": 11.5,
      "rows": 704,
      "total": 6107
    },
    "open_weights": {
      "percent": 41.6,
      "rows": 2539,
      "total": 6107
    },
    "org": {
      "percent": 95.7,
      "rows": 5847,
      "total": 6107
    },
    "params": {
      "percent": 14.8,
      "rows": 906,
      "total": 6107
    },
    "price_in": {
      "percent": 51.9,
      "rows": 3172,
      "total": 6107
    },
    "release_date": {
      "percent": 99.1,
      "rows": 6050,
      "total": 6107
    },
    "trace": {
      "percent": 20.7,
      "rows": 1267,
      "total": 6107
    },
    "uncertainty": {
      "percent": 39.6,
      "rows": 2417,
      "total": 6107
    }
  },
  "gates": {
    "failures": [],
    "status": "pass"
  },
  "generated_at": "2026-11-09T10:43:01Z",
  "status": "warn",
  "warnings": [
    "model metadata conflict: glm-4-5 release_date=2025-08-03/2025-08-05",
    "quarantined benchmark_metadata: empty data or missing Model version",
    "quarantined dtbench: no approved score schema",
    "quarantined ebr_bench: no approved score schema",
    "quarantined eci_scores: empty data or missing Model version",
    "quarantined edi_scores: empty data or missing Model version",
    "quarantined processed_data_for_eci: empty data or missing Model version",
    "quarantined frontiermath_erdos: no approved score schema",
    "quarantined frontiermath_tier_4_v2: no approved score schema",
    "quarantined frontiermath_tiers_1_3_v2: no approved score schema",
    "quarantined frontierswe: expected score column \"Dominance\" missing",
    "quarantined furniture_assembly: no approved score schema",
    "quarantined lmca: no approved score schema",
    "quarantined mirrorcode: no approved score schema",
    "quarantined model_metadata: empty data or missing Model version",
    "quarantined spireclimb: no approved score schema",
    "quarantined spireclimb_sts1_a20_heart: no approved score schema",
    "quarantined spireclimb_sts2_a10: no approved score schema",
    "quarantined weirdml_v3: no approved score schema",
    "quarantined benchmark: benchmark_metadata",
    "quarantined benchmark: dtbench",
    "quarantined benchmark: ebr_bench",
    "quarantined benchmark: eci_scores",
    "quarantined benchmark: edi_scores",
    "quarantined benchmark: processed_data_for_eci",
    "quarantined benchmark: frontiermath_erdos",
    "quarantined benchmark: frontiermath_tier_4_v2",
    "quarantined benchmark: frontiermath_tiers_1_3_v2",
    "quarantined benchmark: frontierswe",
    "quarantined benchmark: furniture_assembly",
    "quarantined benchmark: lmca",
    "quarantined benchmark: mirrorcode",
    "quarantined benchmark: model_metadata",
    "quarantined benchmark: spireclimb",
    "quarantined benchmark: spireclimb_sts1_a20_heart",
    "quarantined benchmark: spireclimb_sts2_a10",
    "quarantined benchmark: weirdml_v3",
    "DeepSWE live source rejected; using Epoch fallback: generated_at is not current: 2026-09-22T06:27:15.860279+00:00"
  ]
}