{
  "source_url": "https://internscience.github.io/ResearchClawBench-Home/data/leaderboard.json",
  "retrieved_at": "2026-10-10",
  "tasks": [
    "Astronomy_000",
    "Astronomy_001",
    "Astronomy_002",
    "Astronomy_003",
    "Chemistry_000",
    "Chemistry_001",
    "Chemistry_002",
    "Chemistry_003",
    "Earth_000",
    "Earth_001",
    "Earth_002",
    "Earth_003",
    "Energy_000",
    "Energy_001",
    "Energy_002",
    "Energy_003",
    "Information_000",
    "Information_001",
    "Information_002",
    "Information_003",
    "Life_000",
    "Life_001",
    "Life_002",
    "Life_003",
    "Material_000",
    "Material_001",
    "Material_002",
    "Material_003",
    "Math_000",
    "Math_001",
    "Math_002",
    "Math_003",
    "Neuroscience_000",
    "Neuroscience_001",
    "Neuroscience_002",
    "Neuroscience_003",
    "Physics_000",
    "Physics_001",
    "Physics_002",
    "Physics_003"
  ],
  "scores": {
    "Claude Code": {
      "Astronomy_000": {
        "score": 23.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_000_20260319_184609",
        "cost_usd": 1.876667,
        "duration_seconds": 563
      },
      "Astronomy_001": {
        "score": 27.4,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_001_20260401_141304",
        "cost_usd": 1.026667,
        "duration_seconds": 308
      },
      "Astronomy_002": {
        "score": 23.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_002_20260401_141959",
        "cost_usd": 2.663333,
        "duration_seconds": 799
      },
      "Astronomy_003": {
        "score": 46.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_003_20260401_143610",
        "cost_usd": 3.593333,
        "duration_seconds": 1078
      },
      "Chemistry_000": {
        "score": 14.75,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_000_20260325_131753",
        "cost_usd": 8.533333,
        "duration_seconds": 2560
      },
      "Chemistry_001": {
        "score": 3.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_001_20260401_145553",
        "cost_usd": 10.106667,
        "duration_seconds": 3032
      },
      "Chemistry_002": {
        "score": 1,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_002_20260401_154822",
        "cost_usd": 10.86,
        "duration_seconds": 3258
      },
      "Chemistry_003": {
        "score": 18,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_003_20260401_190857",
        "cost_usd": 26.433333,
        "duration_seconds": 7930
      },
      "Earth_000": {
        "score": 24.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_000_20260320_014954",
        "cost_usd": 2.013333,
        "duration_seconds": 604
      },
      "Earth_001": {
        "score": 33.56,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_001_20260401_191305",
        "cost_usd": 1.516667,
        "duration_seconds": 455
      },
      "Earth_002": {
        "score": 31.7,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_002_20260401_191349",
        "cost_usd": 2.3,
        "duration_seconds": 690
      },
      "Earth_003": {
        "score": 1,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_003_20260401_191636",
        "cost_usd": 3.49,
        "duration_seconds": 1047
      },
      "Energy_000": {
        "score": 11.3,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_000_20260320_205623",
        "cost_usd": 3.476667,
        "duration_seconds": 1043
      },
      "Energy_001": {
        "score": 21.7,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_001_20260401_191819",
        "cost_usd": 1.543333,
        "duration_seconds": 463
      },
      "Energy_002": {
        "score": 38.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_002_20260401_191836",
        "cost_usd": 4.81,
        "duration_seconds": 1443
      },
      "Energy_003": {
        "score": 15.3,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_003_20260401_200259",
        "cost_usd": 12.163333,
        "duration_seconds": 3649
      },
      "Information_000": {
        "score": 48,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_000_20260325_155748",
        "cost_usd": 2.49,
        "duration_seconds": 747
      },
      "Information_001": {
        "score": 7,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_001_20260401_192424",
        "cost_usd": 1.97,
        "duration_seconds": 591
      },
      "Information_002": {
        "score": 27.1,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_002_20260401_192455",
        "cost_usd": 1.05,
        "duration_seconds": 315
      },
      "Information_003": {
        "score": 17.75,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_003_20260401_224112",
        "cost_usd": 10.346667,
        "duration_seconds": 3104
      },
      "Life_000": {
        "score": 8.2,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_000_20260326_142039",
        "cost_usd": 1.516667,
        "duration_seconds": 455
      },
      "Life_001": {
        "score": 19.55,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_001_20260321_181849",
        "cost_usd": 1.06,
        "duration_seconds": 318
      },
      "Life_002": {
        "score": 6.9,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_002_20260401_200700",
        "cost_usd": 3.573333,
        "duration_seconds": 1072
      },
      "Life_003": {
        "score": 27.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_003_20260401_200717",
        "cost_usd": 0.926667,
        "duration_seconds": 278
      },
      "Material_000": {
        "score": 14.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_000_20260326_144303",
        "cost_usd": 42.28,
        "duration_seconds": 12684
      },
      "Material_001": {
        "score": 23.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_001_20260401_224352",
        "cost_usd": 3.703333,
        "duration_seconds": 1111
      },
      "Material_002": {
        "score": 35.1,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_002_20260401_231210",
        "cost_usd": 2.713333,
        "duration_seconds": 814
      },
      "Material_003": {
        "score": 28.8,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_003_20260401_232634",
        "cost_usd": 7.493333,
        "duration_seconds": 2248
      },
      "Math_000": {
        "score": 26.2,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_000_20260401_233652",
        "cost_usd": 1.863333,
        "duration_seconds": 559
      },
      "Math_001": {
        "score": 44.1,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_001_20260401_235039",
        "cost_usd": 6.153333,
        "duration_seconds": 1846
      },
      "Math_002": {
        "score": 10.2,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_002_20260401_235043",
        "cost_usd": 5.936667,
        "duration_seconds": 1781
      },
      "Math_003": {
        "score": 29.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_003_20260401_235138",
        "cost_usd": 3.863333,
        "duration_seconds": 1159
      },
      "Neuroscience_000": {
        "score": 8.6,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_000_20260321_010354",
        "cost_usd": 1.983333,
        "duration_seconds": 595
      },
      "Neuroscience_001": {
        "score": 4.95,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_001_20260321_182515",
        "cost_usd": 2.23,
        "duration_seconds": 669
      },
      "Neuroscience_002": {
        "score": 0.75,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_002_20260402_002234",
        "cost_usd": 3.33,
        "duration_seconds": 999
      },
      "Neuroscience_003": {
        "score": 7.7,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_003_20260402_011020",
        "cost_usd": 2.376667,
        "duration_seconds": 713
      },
      "Physics_000": {
        "score": 27.4,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_000_20260326_150535",
        "cost_usd": 1.11,
        "duration_seconds": 333
      },
      "Physics_001": {
        "score": 30.25,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_001_20260402_002321",
        "cost_usd": 3.156667,
        "duration_seconds": 947
      },
      "Physics_002": {
        "score": 25.05,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_002_20260402_002341",
        "cost_usd": 1.253333,
        "duration_seconds": 376
      },
      "Physics_003": {
        "score": 46.5,
        "model": "claude-opus-4-6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_003_20260321_135653",
        "cost_usd": 1.26,
        "duration_seconds": 378
      }
    },
    "Codex CLI": {
      "Astronomy_000": {
        "score": 29.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260319_145223",
        "cost_usd": 1.83375,
        "duration_seconds": 978
      },
      "Astronomy_001": {
        "score": 20,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260401_120316",
        "cost_usd": 1.21125,
        "duration_seconds": 646
      },
      "Astronomy_002": {
        "score": 12.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260401_135149",
        "cost_usd": 1.3425,
        "duration_seconds": 716
      },
      "Astronomy_003": {
        "score": 44,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260402_011445",
        "cost_usd": 0.721875,
        "duration_seconds": 385
      },
      "Chemistry_000": {
        "score": 11,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260325_133117",
        "cost_usd": 3.82125,
        "duration_seconds": 2038
      },
      "Chemistry_001": {
        "score": 6.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260402_133326",
        "cost_usd": 2.773125,
        "duration_seconds": 1479
      },
      "Chemistry_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260402_133337",
        "cost_usd": 0.991875,
        "duration_seconds": 529
      },
      "Chemistry_003": {
        "score": 12.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260402_133344",
        "cost_usd": 6.125625,
        "duration_seconds": 3267
      },
      "Earth_000": {
        "score": 25.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260325_142223",
        "cost_usd": 1.16625,
        "duration_seconds": 622
      },
      "Earth_001": {
        "score": 40.87,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260402_020635",
        "cost_usd": 1.16625,
        "duration_seconds": 622
      },
      "Earth_002": {
        "score": 22.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260321_014305",
        "cost_usd": 2.563125,
        "duration_seconds": 1367
      },
      "Earth_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260402_020613",
        "cost_usd": 0.89625,
        "duration_seconds": 478
      },
      "Energy_000": {
        "score": 13.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260325_145840",
        "cost_usd": 1.400625,
        "duration_seconds": 747
      },
      "Energy_001": {
        "score": 24.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260402_021036",
        "cost_usd": 3.478125,
        "duration_seconds": 1855
      },
      "Energy_002": {
        "score": 33,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260402_021822",
        "cost_usd": 1.194375,
        "duration_seconds": 637
      },
      "Energy_003": {
        "score": 21.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260402_021829",
        "cost_usd": 1.464375,
        "duration_seconds": 781
      },
      "Information_000": {
        "score": 10,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260321_012226",
        "cost_usd": 1.186875,
        "duration_seconds": 633
      },
      "Information_001": {
        "score": 5.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260402_023436",
        "cost_usd": 1.303125,
        "duration_seconds": 695
      },
      "Information_002": {
        "score": 36.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260402_023445",
        "cost_usd": 0.97125,
        "duration_seconds": 518
      },
      "Information_003": {
        "score": 15.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260402_023453",
        "cost_usd": 3.553125,
        "duration_seconds": 1895
      },
      "Life_000": {
        "score": 7.55,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260320_211701",
        "cost_usd": 1.633125,
        "duration_seconds": 871
      },
      "Life_001": {
        "score": 12.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260402_024829",
        "cost_usd": 0.79875,
        "duration_seconds": 426
      },
      "Life_002": {
        "score": 1.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260402_024836",
        "cost_usd": 2.199375,
        "duration_seconds": 1173
      },
      "Life_003": {
        "score": 36,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260402_025011",
        "cost_usd": 2.04,
        "duration_seconds": 1088
      },
      "Material_000": {
        "score": 17.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260326_151955",
        "cost_usd": 1.14,
        "duration_seconds": 608
      },
      "Material_001": {
        "score": 11.55,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260402_112556",
        "cost_usd": 1.7475,
        "duration_seconds": 932
      },
      "Material_002": {
        "score": 0.99,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260402_113105",
        "cost_usd": 1.46625,
        "duration_seconds": 782
      },
      "Material_003": {
        "score": 21.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260402_112258",
        "cost_usd": 6.834375,
        "duration_seconds": 3645
      },
      "Math_000": {
        "score": 26.65,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260321_013909",
        "cost_usd": 0.93375,
        "duration_seconds": 498
      },
      "Math_001": {
        "score": 39,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260402_122551",
        "cost_usd": 0.96,
        "duration_seconds": 512
      },
      "Math_002": {
        "score": 7.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260402_122607",
        "cost_usd": 4.595625,
        "duration_seconds": 2451
      },
      "Math_003": {
        "score": 10,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260402_122648",
        "cost_usd": 1.726875,
        "duration_seconds": 921
      },
      "Neuroscience_000": {
        "score": 14,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260402_122827",
        "cost_usd": 1.550625,
        "duration_seconds": 827
      },
      "Neuroscience_001": {
        "score": 2.55,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260402_122849",
        "cost_usd": 1.171875,
        "duration_seconds": 625
      },
      "Neuroscience_002": {
        "score": 2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260402_134508",
        "cost_usd": 6.305625,
        "duration_seconds": 3363
      },
      "Neuroscience_003": {
        "score": 15.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260402_124451",
        "cost_usd": 1.951875,
        "duration_seconds": 1041
      },
      "Physics_000": {
        "score": 32.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260321_011953",
        "cost_usd": 0.976875,
        "duration_seconds": 521
      },
      "Physics_001": {
        "score": 25.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260402_124607",
        "cost_usd": 1.06125,
        "duration_seconds": 566
      },
      "Physics_002": {
        "score": 21.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260402_124626",
        "cost_usd": 1.19625,
        "duration_seconds": 638
      },
      "Physics_003": {
        "score": 45,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260402_125047",
        "cost_usd": 1.0275,
        "duration_seconds": 548
      }
    },
    "ARIS Codex": {
      "Astronomy_000": {
        "score": 16.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260408_123003",
        "cost_usd": 0.63375,
        "duration_seconds": 338
      },
      "Astronomy_001": {
        "score": 10.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260409_012219",
        "cost_usd": 0.5175,
        "duration_seconds": 276
      },
      "Astronomy_002": {
        "score": 11,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260409_012231",
        "cost_usd": 0.556875,
        "duration_seconds": 297
      },
      "Astronomy_003": {
        "score": 47.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260409_012239",
        "cost_usd": 0.3975,
        "duration_seconds": 212
      },
      "Chemistry_000": {
        "score": 15.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260408_152441",
        "cost_usd": 3.345,
        "duration_seconds": 1784
      },
      "Chemistry_001": {
        "score": 2.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260409_091054",
        "cost_usd": 0.73125,
        "duration_seconds": 390
      },
      "Chemistry_002": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260409_091108",
        "cost_usd": 0.72,
        "duration_seconds": 384
      },
      "Chemistry_003": {
        "score": 11.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260409_091136",
        "cost_usd": 0.4725,
        "duration_seconds": 252
      },
      "Earth_000": {
        "score": 14.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260409_004459",
        "cost_usd": 0.568125,
        "duration_seconds": 303
      },
      "Earth_001": {
        "score": 34.48,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260409_092349",
        "cost_usd": 0.44625,
        "duration_seconds": 238
      },
      "Earth_002": {
        "score": 11.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260409_092357",
        "cost_usd": 0.555,
        "duration_seconds": 296
      },
      "Earth_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260409_092406",
        "cost_usd": 0.391875,
        "duration_seconds": 209
      },
      "Energy_000": {
        "score": 10.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260409_001855",
        "cost_usd": 0.448125,
        "duration_seconds": 239
      },
      "Energy_001": {
        "score": 3.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260409_093008",
        "cost_usd": 1.1775,
        "duration_seconds": 628
      },
      "Energy_002": {
        "score": 32.55,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260409_093014",
        "cost_usd": 0.598125,
        "duration_seconds": 319
      },
      "Energy_003": {
        "score": 7.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260409_093023",
        "cost_usd": 0.4575,
        "duration_seconds": 244
      },
      "Information_000": {
        "score": 1.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260409_002925",
        "cost_usd": 0.465,
        "duration_seconds": 248
      },
      "Information_001": {
        "score": 3.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260409_094219",
        "cost_usd": 0.489375,
        "duration_seconds": 261
      },
      "Information_002": {
        "score": 11.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260409_094249",
        "cost_usd": 0.406875,
        "duration_seconds": 217
      },
      "Information_003": {
        "score": 7.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260409_094306",
        "cost_usd": 1.231875,
        "duration_seconds": 657
      },
      "Life_000": {
        "score": 5.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260409_005147",
        "cost_usd": 0.6375,
        "duration_seconds": 340
      },
      "Life_001": {
        "score": 14,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260409_095447",
        "cost_usd": 0.485625,
        "duration_seconds": 259
      },
      "Life_002": {
        "score": 7.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260409_095510",
        "cost_usd": 0.44625,
        "duration_seconds": 238
      },
      "Life_003": {
        "score": 40.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260409_095535",
        "cost_usd": 0.585,
        "duration_seconds": 312
      },
      "Material_000": {
        "score": 11.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260409_005742",
        "cost_usd": 1.273125,
        "duration_seconds": 679
      },
      "Material_001": {
        "score": 8.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260409_100107",
        "cost_usd": 0.433125,
        "duration_seconds": 231
      },
      "Material_002": {
        "score": 11.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260409_113816",
        "cost_usd": 0.55875,
        "duration_seconds": 298
      },
      "Material_003": {
        "score": 18,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260409_100203",
        "cost_usd": 1.0575,
        "duration_seconds": 564
      },
      "Math_000": {
        "score": 7.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260409_011005",
        "cost_usd": 0.5775,
        "duration_seconds": 308
      },
      "Math_001": {
        "score": 31.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260409_101638",
        "cost_usd": 1.333125,
        "duration_seconds": 711
      },
      "Math_002": {
        "score": 6.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260409_101644",
        "cost_usd": 0.97875,
        "duration_seconds": 522
      },
      "Math_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260409_103114",
        "cost_usd": 0.466875,
        "duration_seconds": 249
      },
      "Neuroscience_000": {
        "score": 5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260409_011039",
        "cost_usd": 0.838125,
        "duration_seconds": 447
      },
      "Neuroscience_001": {
        "score": 2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260409_104144",
        "cost_usd": 0.9975,
        "duration_seconds": 532
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260409_104202",
        "cost_usd": 1.299375,
        "duration_seconds": 693
      },
      "Neuroscience_003": {
        "score": 19.65,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260409_104225",
        "cost_usd": 0.525,
        "duration_seconds": 280
      },
      "Physics_000": {
        "score": 18.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260409_011045",
        "cost_usd": 0.613125,
        "duration_seconds": 327
      },
      "Physics_001": {
        "score": 25.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260409_105940",
        "cost_usd": 0.684375,
        "duration_seconds": 365
      },
      "Physics_002": {
        "score": 20,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260409_110111",
        "cost_usd": 0.525,
        "duration_seconds": 280
      },
      "Physics_003": {
        "score": 34.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260409_110326",
        "cost_usd": 0.80625,
        "duration_seconds": 430
      }
    },
    "OpenClaw": {
      "Astronomy_000": {
        "score": 18.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260325_124153",
        "cost_usd": 0.34875,
        "duration_seconds": 186
      },
      "Astronomy_001": {
        "score": 36,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260402_210925",
        "cost_usd": 0.58875,
        "duration_seconds": 314
      },
      "Astronomy_002": {
        "score": 11.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260321_184042",
        "cost_usd": 0.45375,
        "duration_seconds": 242
      },
      "Astronomy_003": {
        "score": 47.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260402_211549",
        "cost_usd": 0.564375,
        "duration_seconds": 301
      },
      "Chemistry_000": {
        "score": 12.85,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260325_142150",
        "cost_usd": 0.864375,
        "duration_seconds": 461
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260402_212107",
        "cost_usd": 0.55125,
        "duration_seconds": 294
      },
      "Chemistry_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260402_212616",
        "cost_usd": 0.6675,
        "duration_seconds": 356
      },
      "Chemistry_003": {
        "score": 9.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260402_213222",
        "cost_usd": 0.999375,
        "duration_seconds": 533
      },
      "Earth_000": {
        "score": 20.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260325_144124",
        "cost_usd": 0.526875,
        "duration_seconds": 281
      },
      "Earth_001": {
        "score": 31.38,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260402_214137",
        "cost_usd": 0.5175,
        "duration_seconds": 276
      },
      "Earth_002": {
        "score": 16.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260402_214628",
        "cost_usd": 0.841875,
        "duration_seconds": 449
      },
      "Earth_003": {
        "score": 0.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260402_215412",
        "cost_usd": 0.53625,
        "duration_seconds": 286
      },
      "Energy_000": {
        "score": 16,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260325_151822",
        "cost_usd": 0.680625,
        "duration_seconds": 363
      },
      "Energy_001": {
        "score": 15.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260402_215912",
        "cost_usd": 1.141875,
        "duration_seconds": 609
      },
      "Energy_002": {
        "score": 31,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260321_150347",
        "cost_usd": 0.62625,
        "duration_seconds": 334
      },
      "Energy_003": {
        "score": 25.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260402_220933",
        "cost_usd": 0.60375,
        "duration_seconds": 322
      },
      "Information_000": {
        "score": 35.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260325_163554",
        "cost_usd": 0.4275,
        "duration_seconds": 228
      },
      "Information_001": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260402_221510",
        "cost_usd": 0.579375,
        "duration_seconds": 309
      },
      "Information_002": {
        "score": 15.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260402_222052",
        "cost_usd": 0.41625,
        "duration_seconds": 222
      },
      "Information_003": {
        "score": 5.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260402_222436",
        "cost_usd": 1.06875,
        "duration_seconds": 570
      },
      "Life_000": {
        "score": 5.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260326_142858",
        "cost_usd": 0.676875,
        "duration_seconds": 361
      },
      "Life_001": {
        "score": 13.35,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260402_223418",
        "cost_usd": 0.534375,
        "duration_seconds": 285
      },
      "Life_002": {
        "score": 9.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260321_145056",
        "cost_usd": 0.82125,
        "duration_seconds": 438
      },
      "Life_003": {
        "score": 34.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260402_223914",
        "cost_usd": 0.6675,
        "duration_seconds": 356
      },
      "Material_000": {
        "score": 12,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260326_145735",
        "cost_usd": 0.70125,
        "duration_seconds": 374
      },
      "Material_001": {
        "score": 13.45,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260402_224523",
        "cost_usd": 0.515625,
        "duration_seconds": 275
      },
      "Material_002": {
        "score": 6.12,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260402_225007",
        "cost_usd": 0.74625,
        "duration_seconds": 398
      },
      "Material_003": {
        "score": 20.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260402_225655",
        "cost_usd": 0.571875,
        "duration_seconds": 305
      },
      "Math_000": {
        "score": 24.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260402_230222",
        "cost_usd": 1.029375,
        "duration_seconds": 549
      },
      "Math_001": {
        "score": 23.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260402_231143",
        "cost_usd": 0.560625,
        "duration_seconds": 299
      },
      "Math_002": {
        "score": 8.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260402_231652",
        "cost_usd": 0.725625,
        "duration_seconds": 387
      },
      "Math_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260402_232335",
        "cost_usd": 0.526875,
        "duration_seconds": 281
      },
      "Neuroscience_000": {
        "score": 13.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260402_232819",
        "cost_usd": 0.63,
        "duration_seconds": 336
      },
      "Neuroscience_001": {
        "score": 3.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260402_233406",
        "cost_usd": 0.69,
        "duration_seconds": 368
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260402_234030",
        "cost_usd": 1.955625,
        "duration_seconds": 1043
      },
      "Neuroscience_003": {
        "score": 15.05,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260402_235804",
        "cost_usd": 0.688125,
        "duration_seconds": 367
      },
      "Physics_000": {
        "score": 7.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260326_151120",
        "cost_usd": 0.51,
        "duration_seconds": 272
      },
      "Physics_001": {
        "score": 32,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260403_000425",
        "cost_usd": 0.735,
        "duration_seconds": 392
      },
      "Physics_002": {
        "score": 27.45,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260403_001108",
        "cost_usd": 0.613125,
        "duration_seconds": 327
      },
      "Physics_003": {
        "score": 43.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260403_001651",
        "cost_usd": 0.523125,
        "duration_seconds": 279
      }
    },
    "Nanobot": {
      "Astronomy_000": {
        "score": 14.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260325_124221",
        "cost_usd": 0.485625,
        "duration_seconds": 259
      },
      "Astronomy_001": {
        "score": 20.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260331_192927",
        "cost_usd": 0.28875,
        "duration_seconds": 154
      },
      "Astronomy_002": {
        "score": 10,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260331_193218",
        "cost_usd": 0.27375,
        "duration_seconds": 146
      },
      "Astronomy_003": {
        "score": 44.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260331_193503",
        "cost_usd": 0.189375,
        "duration_seconds": 101
      },
      "Chemistry_000": {
        "score": 16.85,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260320_193804",
        "cost_usd": 3.811875,
        "duration_seconds": 2033
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260331_194645",
        "cost_usd": 0.465,
        "duration_seconds": 248
      },
      "Chemistry_002": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260331_195151",
        "cost_usd": 0.16875,
        "duration_seconds": 90
      },
      "Chemistry_003": {
        "score": 7.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260331_195455",
        "cost_usd": 0.418125,
        "duration_seconds": 223
      },
      "Earth_000": {
        "score": 21.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260325_135520",
        "cost_usd": 0.826875,
        "duration_seconds": 441
      },
      "Earth_001": {
        "score": 25.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260331_201226",
        "cost_usd": 0.148125,
        "duration_seconds": 79
      },
      "Earth_002": {
        "score": 9.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260331_201408",
        "cost_usd": 0.49125,
        "duration_seconds": 262
      },
      "Earth_003": {
        "score": 0.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260331_201851",
        "cost_usd": 0.16125,
        "duration_seconds": 86
      },
      "Energy_000": {
        "score": 9.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260325_151836",
        "cost_usd": 0.905625,
        "duration_seconds": 483
      },
      "Energy_001": {
        "score": 7.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260331_200332",
        "cost_usd": 0.429375,
        "duration_seconds": 229
      },
      "Energy_002": {
        "score": 27.85,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260331_200739",
        "cost_usd": 0.31125,
        "duration_seconds": 166
      },
      "Energy_003": {
        "score": 9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260331_201029",
        "cost_usd": 0.189375,
        "duration_seconds": 101
      },
      "Information_000": {
        "score": 22.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260325_164339",
        "cost_usd": 0.508125,
        "duration_seconds": 271
      },
      "Information_001": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260331_202137",
        "cost_usd": 0.256875,
        "duration_seconds": 137
      },
      "Information_002": {
        "score": 11.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260331_202504",
        "cost_usd": 0.27375,
        "duration_seconds": 146
      },
      "Information_003": {
        "score": 9.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260331_202744",
        "cost_usd": 1.665,
        "duration_seconds": 888
      },
      "Life_000": {
        "score": 7.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260401_111247",
        "cost_usd": 0.61125,
        "duration_seconds": 326
      },
      "Life_001": {
        "score": 9.65,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260401_111910",
        "cost_usd": 0.18375,
        "duration_seconds": 98
      },
      "Life_002": {
        "score": 4.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260401_112219",
        "cost_usd": 0.301875,
        "duration_seconds": 161
      },
      "Life_003": {
        "score": 29.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260401_112646",
        "cost_usd": 0.4275,
        "duration_seconds": 228
      },
      "Material_000": {
        "score": 23,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260321_132712",
        "cost_usd": 1.00875,
        "duration_seconds": 538
      },
      "Material_001": {
        "score": 1.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260401_113052",
        "cost_usd": 0.166875,
        "duration_seconds": 89
      },
      "Material_002": {
        "score": 14.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260401_115629",
        "cost_usd": 0.294375,
        "duration_seconds": 157
      },
      "Material_003": {
        "score": 12.35,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260401_115948",
        "cost_usd": 0.275625,
        "duration_seconds": 147
      },
      "Math_000": {
        "score": 17.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260401_120618",
        "cost_usd": 0.414375,
        "duration_seconds": 221
      },
      "Math_001": {
        "score": 30.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260401_121718",
        "cost_usd": 0.165,
        "duration_seconds": 88
      },
      "Math_002": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260401_122108",
        "cost_usd": 0.234375,
        "duration_seconds": 125
      },
      "Math_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260401_122803",
        "cost_usd": 0.24375,
        "duration_seconds": 130
      },
      "Neuroscience_000": {
        "score": 7.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260401_123535",
        "cost_usd": 0.234375,
        "duration_seconds": 125
      },
      "Neuroscience_001": {
        "score": 1.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260401_123958",
        "cost_usd": 0.1875,
        "duration_seconds": 100
      },
      "Neuroscience_002": {
        "score": 0.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260401_124612",
        "cost_usd": 0.553125,
        "duration_seconds": 295
      },
      "Neuroscience_003": {
        "score": 4.25,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260401_125606",
        "cost_usd": 0.290625,
        "duration_seconds": 155
      },
      "Physics_000": {
        "score": 7.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260326_151123",
        "cost_usd": 0.646875,
        "duration_seconds": 345
      },
      "Physics_001": {
        "score": 27.45,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260401_130120",
        "cost_usd": 0.399375,
        "duration_seconds": 213
      },
      "Physics_002": {
        "score": 10.35,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260401_130518",
        "cost_usd": 0.36375,
        "duration_seconds": 194
      },
      "Physics_003": {
        "score": 31.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260401_131002",
        "cost_usd": 0.26625,
        "duration_seconds": 142
      }
    },
    "ResearchClaw": {
      "Astronomy_000": {
        "score": 20.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260409_104742",
        "cost_usd": 0.534375,
        "duration_seconds": 285
      },
      "Astronomy_001": {
        "score": 14.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260408_180204",
        "cost_usd": 0.478125,
        "duration_seconds": 255
      },
      "Astronomy_002": {
        "score": 11.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260408_182333",
        "cost_usd": 0.73125,
        "duration_seconds": 390
      },
      "Astronomy_003": {
        "score": 45.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260408_183133",
        "cost_usd": 0.399375,
        "duration_seconds": 213
      },
      "Chemistry_000": {
        "score": 18.25,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260409_105911",
        "cost_usd": 3.504375,
        "duration_seconds": 1869
      },
      "Chemistry_001": {
        "score": 2.15,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260409_113212",
        "cost_usd": 0.418125,
        "duration_seconds": 223
      },
      "Chemistry_002": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260409_114123",
        "cost_usd": 0.4275,
        "duration_seconds": 228
      },
      "Chemistry_003": {
        "score": 13.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260409_114635",
        "cost_usd": 0.64875,
        "duration_seconds": 346
      },
      "Earth_000": {
        "score": 14.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260409_115522",
        "cost_usd": 0.556875,
        "duration_seconds": 297
      },
      "Earth_001": {
        "score": 32.97,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260409_120559",
        "cost_usd": 0.68625,
        "duration_seconds": 366
      },
      "Earth_002": {
        "score": 20.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260409_130041",
        "cost_usd": 0.545625,
        "duration_seconds": 291
      },
      "Earth_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260409_130946",
        "cost_usd": 0.324375,
        "duration_seconds": 173
      },
      "Energy_000": {
        "score": 3.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260409_134154",
        "cost_usd": 0.481875,
        "duration_seconds": 257
      },
      "Energy_001": {
        "score": 15.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260409_135102",
        "cost_usd": 0.519375,
        "duration_seconds": 277
      },
      "Energy_002": {
        "score": 37.65,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260409_135612",
        "cost_usd": 0.564375,
        "duration_seconds": 301
      },
      "Energy_003": {
        "score": 19.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260409_142519",
        "cost_usd": 0.3225,
        "duration_seconds": 172
      },
      "Information_000": {
        "score": 10,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260409_150604",
        "cost_usd": 0.358125,
        "duration_seconds": 191
      },
      "Information_001": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260409_154703",
        "cost_usd": 0.45375,
        "duration_seconds": 242
      },
      "Information_002": {
        "score": 39.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260409_155531",
        "cost_usd": 0.42,
        "duration_seconds": 224
      },
      "Information_003": {
        "score": 9.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260409_161445",
        "cost_usd": 2.01,
        "duration_seconds": 1072
      },
      "Life_000": {
        "score": 10.05,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260409_173006",
        "cost_usd": 1.625625,
        "duration_seconds": 867
      },
      "Life_001": {
        "score": 5.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260409_171658",
        "cost_usd": 0.496875,
        "duration_seconds": 265
      },
      "Life_002": {
        "score": 6.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260409_184513",
        "cost_usd": 0.4725,
        "duration_seconds": 252
      },
      "Life_003": {
        "score": 33.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260409_192448",
        "cost_usd": 0.57375,
        "duration_seconds": 306
      },
      "Material_000": {
        "score": 12.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260410_135328",
        "cost_usd": 0.85875,
        "duration_seconds": 458
      },
      "Material_001": {
        "score": 12.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260410_141525",
        "cost_usd": 0.609375,
        "duration_seconds": 325
      },
      "Material_002": {
        "score": 35.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260410_142401",
        "cost_usd": 2.0775,
        "duration_seconds": 1108
      },
      "Material_003": {
        "score": 16.25,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260410_145941",
        "cost_usd": 0.50625,
        "duration_seconds": 270
      },
      "Math_000": {
        "score": 7.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260410_150535",
        "cost_usd": 0.3675,
        "duration_seconds": 196
      },
      "Math_001": {
        "score": 37.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260410_151201",
        "cost_usd": 0.3225,
        "duration_seconds": 172
      },
      "Math_002": {
        "score": 6.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260410_151706",
        "cost_usd": 2.94,
        "duration_seconds": 1568
      },
      "Math_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260410_154450",
        "cost_usd": 0.39,
        "duration_seconds": 208
      },
      "Neuroscience_000": {
        "score": 7.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260410_155023",
        "cost_usd": 0.511875,
        "duration_seconds": 273
      },
      "Neuroscience_001": {
        "score": 0.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260410_155818",
        "cost_usd": 0.388125,
        "duration_seconds": 207
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260410_160729",
        "cost_usd": 4.15125,
        "duration_seconds": 2214
      },
      "Neuroscience_003": {
        "score": 7.35,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260410_164642",
        "cost_usd": 0.459375,
        "duration_seconds": 245
      },
      "Physics_000": {
        "score": 22.7,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260410_165157",
        "cost_usd": 0.28125,
        "duration_seconds": 150
      },
      "Physics_001": {
        "score": 29.25,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260410_170205",
        "cost_usd": 0.489375,
        "duration_seconds": 261
      },
      "Physics_002": {
        "score": 24.25,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260410_171139",
        "cost_usd": 0.42375,
        "duration_seconds": 226
      },
      "Physics_003": {
        "score": 44.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260410_171712",
        "cost_usd": 0.320625,
        "duration_seconds": 171
      }
    },
    "AutoSciRub": {
      "Astronomy_000": {
        "score": 42.7,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Astronomy_000_20260831_130422",
        "cost_usd": 5.245333,
        "duration_seconds": 1967
      },
      "Astronomy_001": {
        "score": 41.4,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Astronomy_001_20260830_232802",
        "cost_usd": 3.52,
        "duration_seconds": 1320
      },
      "Astronomy_002": {
        "score": 34.97,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Astronomy_002_20260831_130422",
        "cost_usd": 6.178667,
        "duration_seconds": 2317
      },
      "Astronomy_003": {
        "score": 50,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Astronomy_003_20260831_130422",
        "cost_usd": 3.101333,
        "duration_seconds": 1163
      },
      "Chemistry_000": {
        "score": 35.13,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Chemistry_000_20260831_230434",
        "cost_usd": 29.656,
        "duration_seconds": 11121
      },
      "Chemistry_001": {
        "score": 7.9,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Chemistry_001_20260831_133122",
        "cost_usd": 4.525333,
        "duration_seconds": 1697
      },
      "Chemistry_002": {
        "score": 38.02,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Chemistry_002_20260831_133722",
        "cost_usd": 7.274667,
        "duration_seconds": 2728
      },
      "Chemistry_003": {
        "score": 39.27,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Chemistry_003_20260901_124456",
        "cost_usd": 7.12,
        "duration_seconds": 2670
      },
      "Earth_000": {
        "score": 34.43,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Earth_000_20260831_140022",
        "cost_usd": 4.968,
        "duration_seconds": 1863
      },
      "Earth_001": {
        "score": 47.06,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Earth_001_20260831_143622",
        "cost_usd": 5.426667,
        "duration_seconds": 2035
      },
      "Earth_002": {
        "score": 38.37,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Earth_002_20260831_230434",
        "cost_usd": 9.717333,
        "duration_seconds": 3644
      },
      "Earth_003": {
        "score": 0.87,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Earth_003_20260901_154317",
        "cost_usd": 3.714667,
        "duration_seconds": 1393
      },
      "Energy_000": {
        "score": 20.4,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Energy_000_20260830_225502",
        "cost_usd": 7.152,
        "duration_seconds": 2682
      },
      "Energy_001": {
        "score": 36.47,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Energy_001_20260831_151023",
        "cost_usd": 7.005333,
        "duration_seconds": 2627
      },
      "Energy_002": {
        "score": 42.25,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Energy_002_20260831_153123",
        "cost_usd": 5.608,
        "duration_seconds": 2103
      },
      "Energy_003": {
        "score": 27.7,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Energy_003_20260831_154123",
        "cost_usd": 5.269333,
        "duration_seconds": 1976
      },
      "Information_000": {
        "score": 33.97,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Information_000_20260831_155423",
        "cost_usd": 10.085333,
        "duration_seconds": 3782
      },
      "Information_001": {
        "score": 20.47,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Information_001_20260901_151417",
        "cost_usd": 4.866667,
        "duration_seconds": 1825
      },
      "Information_002": {
        "score": 49.63,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Information_002_20260831_161423",
        "cost_usd": 5.130667,
        "duration_seconds": 1924
      },
      "Information_003": {
        "score": 29.85,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Information_003_20260831_161423",
        "cost_usd": 10.426667,
        "duration_seconds": 3910
      },
      "Life_000": {
        "score": 28.78,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Life_000_20260831_164723",
        "cost_usd": 8.026667,
        "duration_seconds": 3010
      },
      "Life_001": {
        "score": 19.28,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Life_001_20260901_154917",
        "cost_usd": 4.613333,
        "duration_seconds": 1730
      },
      "Life_002": {
        "score": 17.8,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Life_002_20260831_172024",
        "cost_usd": 7.552,
        "duration_seconds": 2832
      },
      "Life_003": {
        "score": 39.1,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Life_003_20260831_173824",
        "cost_usd": 7.634667,
        "duration_seconds": 2863
      },
      "Material_000": {
        "score": 30.73,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Material_000_20260831_174524",
        "cost_usd": 8.594667,
        "duration_seconds": 3223
      },
      "Material_001": {
        "score": 28.58,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Material_001_20260831_180824",
        "cost_usd": 7.466667,
        "duration_seconds": 2800
      },
      "Material_002": {
        "score": 39.39,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Material_002_20260831_182224",
        "cost_usd": 6.650667,
        "duration_seconds": 2494
      },
      "Material_003": {
        "score": 39.13,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Material_003_20260831_182624",
        "cost_usd": 7.877333,
        "duration_seconds": 2954
      },
      "Math_000": {
        "score": 32.75,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Math_000_20260901_120956",
        "cost_usd": 6.32,
        "duration_seconds": 2370
      },
      "Math_001": {
        "score": 25.43,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Math_001_20260901_120556",
        "cost_usd": 6.213333,
        "duration_seconds": 2330
      },
      "Math_002": {
        "score": 37.4,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Math_002_20260831_001503",
        "cost_usd": 10.504,
        "duration_seconds": 3939
      },
      "Math_003": {
        "score": 19.67,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Math_003_20260831_230435",
        "cost_usd": 11.437333,
        "duration_seconds": 4289
      },
      "Neuroscience_000": {
        "score": 9.8,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Neuroscience_000_20260901_151417",
        "cost_usd": 5.514667,
        "duration_seconds": 2068
      },
      "Neuroscience_001": {
        "score": 36.37,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Neuroscience_001_20260831_193924",
        "cost_usd": 14.986667,
        "duration_seconds": 5620
      },
      "Neuroscience_002": {
        "score": 23.08,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Neuroscience_002_20260830_225502",
        "cost_usd": 5.221333,
        "duration_seconds": 1958
      },
      "Neuroscience_003": {
        "score": 50.78,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Neuroscience_003_20260831_203625",
        "cost_usd": 16.96,
        "duration_seconds": 6360
      },
      "Physics_000": {
        "score": 48.7,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Physics_000_20260831_210225",
        "cost_usd": 7.381333,
        "duration_seconds": 2768
      },
      "Physics_001": {
        "score": 30.98,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Physics_001_20260901_120956",
        "cost_usd": 6.152,
        "duration_seconds": 2307
      },
      "Physics_002": {
        "score": 51.27,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Physics_002_20260831_211625",
        "cost_usd": 10.829333,
        "duration_seconds": 4061
      },
      "Physics_003": {
        "score": 46.47,
        "model": "gpt-5.6-sol",
        "model_display": "Codex GPT-5.6-Sol",
        "run_id": "Physics_003_20260831_214925",
        "cost_usd": 8.032,
        "duration_seconds": 3012
      }
    },
    "EvoLab": {
      "Astronomy_000": {
        "score": 40.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_000_20260817_164021",
        "cost_usd": 2.688645,
        "duration_seconds": 716.972
      },
      "Astronomy_001": {
        "score": 41.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_001_20260817_164021",
        "cost_usd": 4.385018,
        "duration_seconds": 1169.338
      },
      "Astronomy_002": {
        "score": 35,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_002_20260817_164021",
        "cost_usd": 6.116644,
        "duration_seconds": 1631.105
      },
      "Astronomy_003": {
        "score": 62,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_003_20260817_164021",
        "cost_usd": 3.072626,
        "duration_seconds": 819.367
      },
      "Chemistry_000": {
        "score": 29.1,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_000_20260817_164021",
        "cost_usd": 15.631286,
        "duration_seconds": 4168.343
      },
      "Chemistry_001": {
        "score": 22.75,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_001_20260817_164021",
        "cost_usd": 5.639617,
        "duration_seconds": 1503.898
      },
      "Chemistry_002": {
        "score": 24.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_002_20260817_164021",
        "cost_usd": 4.139314,
        "duration_seconds": 1103.817
      },
      "Chemistry_003": {
        "score": 33.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_003_20260817_164021",
        "cost_usd": 17.656316,
        "duration_seconds": 4708.351
      },
      "Earth_000": {
        "score": 25.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_000_20260817_164021",
        "cost_usd": 4.267069,
        "duration_seconds": 1137.885
      },
      "Earth_001": {
        "score": 39.61,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_001_20260817_164021",
        "cost_usd": 4.395986,
        "duration_seconds": 1172.263
      },
      "Earth_002": {
        "score": 31.1,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_002_20260817_164021",
        "cost_usd": 10.144684,
        "duration_seconds": 2705.249
      },
      "Earth_003": {
        "score": 22.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_003_20260817_164021",
        "cost_usd": 4.012695,
        "duration_seconds": 1070.052
      },
      "Energy_000": {
        "score": 19.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_000_20260817_164021",
        "cost_usd": 9.760129,
        "duration_seconds": 2602.701
      },
      "Energy_001": {
        "score": 45.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_001_20260817_164021",
        "cost_usd": 4.87818,
        "duration_seconds": 1300.848
      },
      "Energy_002": {
        "score": 41.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_002_20260817_164021",
        "cost_usd": 9.378086,
        "duration_seconds": 2500.823
      },
      "Energy_003": {
        "score": 29.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_003_20260817_164021",
        "cost_usd": 4.170094,
        "duration_seconds": 1112.025
      },
      "Information_000": {
        "score": 32.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_000_20260817_164021",
        "cost_usd": 10.088377,
        "duration_seconds": 2690.234
      },
      "Information_001": {
        "score": 50.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_001_20260817_164021",
        "cost_usd": 4.081166,
        "duration_seconds": 1088.311
      },
      "Information_002": {
        "score": 51.1,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_002_20260817_164021",
        "cost_usd": 3.486514,
        "duration_seconds": 929.737
      },
      "Information_003": {
        "score": 18,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_003_20260817_164021",
        "cost_usd": 6.84102,
        "duration_seconds": 1824.272
      },
      "Life_000": {
        "score": 20.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_000_20260817_164021",
        "cost_usd": 3.329134,
        "duration_seconds": 887.769
      },
      "Life_001": {
        "score": 15.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_001_20260817_164021",
        "cost_usd": 3.130313,
        "duration_seconds": 834.75
      },
      "Life_002": {
        "score": 42.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_002_20260817_164021",
        "cost_usd": 5.195032,
        "duration_seconds": 1385.342
      },
      "Life_003": {
        "score": 36.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_003_20260817_164021",
        "cost_usd": 3.781324,
        "duration_seconds": 1008.353
      },
      "Material_000": {
        "score": 34.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_000_20260817_164021",
        "cost_usd": 8.557155,
        "duration_seconds": 2281.908
      },
      "Material_001": {
        "score": 20.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_001_20260817_164021",
        "cost_usd": 6.753037,
        "duration_seconds": 1800.81
      },
      "Material_002": {
        "score": 21.73,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_002_20260817_164021",
        "cost_usd": 3.863775,
        "duration_seconds": 1030.34
      },
      "Material_003": {
        "score": 22.85,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_003_20260817_164021",
        "cost_usd": 4.659319,
        "duration_seconds": 1242.485
      },
      "Math_000": {
        "score": 25.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_000_20260817_164021",
        "cost_usd": 4.776656,
        "duration_seconds": 1273.775
      },
      "Math_001": {
        "score": 47.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_001_20260817_164021",
        "cost_usd": 3.072791,
        "duration_seconds": 819.411
      },
      "Math_002": {
        "score": 28.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_002_20260817_164021",
        "cost_usd": 9.752265,
        "duration_seconds": 2600.604
      },
      "Math_003": {
        "score": 8.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_003_20260817_164021",
        "cost_usd": 3.803344,
        "duration_seconds": 1014.225
      },
      "Neuroscience_000": {
        "score": 22.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_000_20260817_164021",
        "cost_usd": 20.175634,
        "duration_seconds": 5380.169
      },
      "Neuroscience_001": {
        "score": 15.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_001_20260817_164021",
        "cost_usd": 5.144561,
        "duration_seconds": 1371.883
      },
      "Neuroscience_002": {
        "score": 11.15,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_002_20260817_164021",
        "cost_usd": 4.356517,
        "duration_seconds": 1161.738
      },
      "Neuroscience_003": {
        "score": 31.85,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_003_20260817_164021",
        "cost_usd": 7.793351,
        "duration_seconds": 2078.227
      },
      "Physics_000": {
        "score": 42.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_000_20260817_164021",
        "cost_usd": 5.343015,
        "duration_seconds": 1424.804
      },
      "Physics_001": {
        "score": 43.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_001_20260817_164021",
        "cost_usd": 10.450223,
        "duration_seconds": 2786.726
      },
      "Physics_002": {
        "score": 53.85,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_002_20260817_164021",
        "cost_usd": 4.290026,
        "duration_seconds": 1144.007
      },
      "Physics_003": {
        "score": 65.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_003_20260817_164021",
        "cost_usd": 5.026987,
        "duration_seconds": 1340.53
      }
    },
    "EvoScientist (0.0.4)": {
      "Astronomy_000": {
        "score": 11.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260330_094408",
        "cost_usd": 1.280625,
        "duration_seconds": 683
      },
      "Astronomy_001": {
        "score": 21.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260403_194127",
        "cost_usd": 0.7875,
        "duration_seconds": 420
      },
      "Astronomy_002": {
        "score": 23.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260404_132455",
        "cost_usd": 0.76875,
        "duration_seconds": 410
      },
      "Astronomy_003": {
        "score": 47.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260404_133145",
        "cost_usd": 0.39,
        "duration_seconds": 208
      },
      "Chemistry_000": {
        "score": 7.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260330_095531",
        "cost_usd": 5.07375,
        "duration_seconds": 2706
      },
      "Chemistry_001": {
        "score": 7.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260404_133513",
        "cost_usd": 0.68625,
        "duration_seconds": 366
      },
      "Chemistry_002": {
        "score": 1.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260404_134119",
        "cost_usd": 0.639375,
        "duration_seconds": 341
      },
      "Chemistry_003": {
        "score": 1.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260404_134700",
        "cost_usd": 1.363125,
        "duration_seconds": 727
      },
      "Earth_000": {
        "score": 12.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260330_104037",
        "cost_usd": 0.523125,
        "duration_seconds": 279
      },
      "Earth_001": {
        "score": 39.97,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260404_135907",
        "cost_usd": 0.429375,
        "duration_seconds": 229
      },
      "Earth_002": {
        "score": 15.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260404_140256",
        "cost_usd": 0.915,
        "duration_seconds": 488
      },
      "Earth_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260404_141105",
        "cost_usd": 0.931875,
        "duration_seconds": 497
      },
      "Energy_000": {
        "score": 12.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260330_104517",
        "cost_usd": 2.79,
        "duration_seconds": 1488
      },
      "Energy_001": {
        "score": 20.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260404_141923",
        "cost_usd": 0.7575,
        "duration_seconds": 404
      },
      "Energy_002": {
        "score": 36.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260404_142606",
        "cost_usd": 0.57,
        "duration_seconds": 304
      },
      "Energy_003": {
        "score": 26.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260404_143111",
        "cost_usd": 0.63,
        "duration_seconds": 336
      },
      "Information_000": {
        "score": 7.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260330_111006",
        "cost_usd": 0.789375,
        "duration_seconds": 421
      },
      "Information_001": {
        "score": 3.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260404_143647",
        "cost_usd": 1.025625,
        "duration_seconds": 547
      },
      "Information_002": {
        "score": 14.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260404_144554",
        "cost_usd": 0.583125,
        "duration_seconds": 311
      },
      "Information_003": {
        "score": 4.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260404_145105",
        "cost_usd": 2.63625,
        "duration_seconds": 1406
      },
      "Life_000": {
        "score": 7.05,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260330_111707",
        "cost_usd": 1.31625,
        "duration_seconds": 702
      },
      "Life_001": {
        "score": 13.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260404_151432",
        "cost_usd": 0.624375,
        "duration_seconds": 333
      },
      "Life_002": {
        "score": 9.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260404_152005",
        "cost_usd": 0.38625,
        "duration_seconds": 206
      },
      "Life_003": {
        "score": 36,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260404_152331",
        "cost_usd": 0.7275,
        "duration_seconds": 388
      },
      "Material_000": {
        "score": 17.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260330_112849",
        "cost_usd": 3.838125,
        "duration_seconds": 2047
      },
      "Material_001": {
        "score": 6.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260404_152959",
        "cost_usd": 0.605625,
        "duration_seconds": 323
      },
      "Material_002": {
        "score": 10.05,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260404_153523",
        "cost_usd": 0.448125,
        "duration_seconds": 239
      },
      "Material_003": {
        "score": 19.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260404_153922",
        "cost_usd": 1.831875,
        "duration_seconds": 977
      },
      "Math_000": {
        "score": 8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260330_120257",
        "cost_usd": 1.0725,
        "duration_seconds": 572
      },
      "Math_001": {
        "score": 35.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260404_155539",
        "cost_usd": 0.78,
        "duration_seconds": 416
      },
      "Math_002": {
        "score": 14.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260404_160235",
        "cost_usd": 1.1025,
        "duration_seconds": 588
      },
      "Math_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260404_161228",
        "cost_usd": 0.639375,
        "duration_seconds": 341
      },
      "Neuroscience_000": {
        "score": 13.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260330_121229",
        "cost_usd": 0.999375,
        "duration_seconds": 533
      },
      "Neuroscience_001": {
        "score": 0.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260404_161809",
        "cost_usd": 0.89625,
        "duration_seconds": 478
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260404_162607",
        "cost_usd": 4.27875,
        "duration_seconds": 2282
      },
      "Neuroscience_003": {
        "score": 5.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260404_170410",
        "cost_usd": 1.171875,
        "duration_seconds": 625
      },
      "Physics_000": {
        "score": 19.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260330_122122",
        "cost_usd": 0.73125,
        "duration_seconds": 390
      },
      "Physics_001": {
        "score": 24.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260404_171435",
        "cost_usd": 0.66375,
        "duration_seconds": 354
      },
      "Physics_002": {
        "score": 24.85,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260404_172029",
        "cost_usd": 1.48875,
        "duration_seconds": 794
      },
      "Physics_003": {
        "score": 36.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260404_173350",
        "cost_usd": 0.601875,
        "duration_seconds": 321
      }
    },
    "EvoScientist (0.1.1)": {
      "Astronomy_000": {
        "score": 24,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260601_183010",
        "cost_usd": 2.99625,
        "duration_seconds": 1598
      },
      "Astronomy_001": {
        "score": 12.8,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260601_201927",
        "cost_usd": 1.501875,
        "duration_seconds": 801
      },
      "Astronomy_002": {
        "score": 23.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260601_203302",
        "cost_usd": 3.024375,
        "duration_seconds": 1613
      },
      "Astronomy_003": {
        "score": 45.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260601_210013",
        "cost_usd": 0.898125,
        "duration_seconds": 479
      },
      "Chemistry_000": {
        "score": 9.55,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260601_210836",
        "cost_usd": 3.70125,
        "duration_seconds": 1974
      },
      "Chemistry_001": {
        "score": 11.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260601_214144",
        "cost_usd": 6.005625,
        "duration_seconds": 3203
      },
      "Chemistry_002": {
        "score": 3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260601_223531",
        "cost_usd": 2.473125,
        "duration_seconds": 1319
      },
      "Chemistry_003": {
        "score": 15.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260601_225747",
        "cost_usd": 6.70125,
        "duration_seconds": 3574
      },
      "Earth_000": {
        "score": 23,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260602_084348",
        "cost_usd": 2.3925,
        "duration_seconds": 1276
      },
      "Earth_001": {
        "score": 39.36,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260602_090906",
        "cost_usd": 1.12875,
        "duration_seconds": 602
      },
      "Earth_002": {
        "score": 13,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260602_091948",
        "cost_usd": 2.71125,
        "duration_seconds": 1446
      },
      "Earth_003": {
        "score": 0,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260602_103953",
        "cost_usd": 4.629375,
        "duration_seconds": 2469
      },
      "Energy_000": {
        "score": 9.9,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260602_112130",
        "cost_usd": 5.293125,
        "duration_seconds": 2823
      },
      "Energy_001": {
        "score": 16.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260602_120851",
        "cost_usd": 2.50875,
        "duration_seconds": 1338
      },
      "Energy_002": {
        "score": 33.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260602_123324",
        "cost_usd": 8.92875,
        "duration_seconds": 4762
      },
      "Energy_003": {
        "score": 19.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260602_144640",
        "cost_usd": 3.714375,
        "duration_seconds": 1981
      },
      "Information_000": {
        "score": 24.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260602_152014",
        "cost_usd": 1.93875,
        "duration_seconds": 1034
      },
      "Information_001": {
        "score": 2.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260602_160625",
        "cost_usd": 2.690625,
        "duration_seconds": 1435
      },
      "Information_002": {
        "score": 35,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260602_163049",
        "cost_usd": 2.548125,
        "duration_seconds": 1359
      },
      "Information_003": {
        "score": 13.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260602_165333",
        "cost_usd": 5.176875,
        "duration_seconds": 2761
      },
      "Life_000": {
        "score": 9.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260602_173947",
        "cost_usd": 4.83375,
        "duration_seconds": 2578
      },
      "Life_001": {
        "score": 5.95,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260602_182305",
        "cost_usd": 2.953125,
        "duration_seconds": 1575
      },
      "Life_002": {
        "score": 11.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260602_184939",
        "cost_usd": 5.4225,
        "duration_seconds": 2892
      },
      "Life_003": {
        "score": 40.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260602_203549",
        "cost_usd": 2.6775,
        "duration_seconds": 1428
      },
      "Material_000": {
        "score": 5.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260602_210002",
        "cost_usd": 4.9125,
        "duration_seconds": 2620
      },
      "Material_001": {
        "score": 3.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260602_214354",
        "cost_usd": 2.1,
        "duration_seconds": 1120
      },
      "Material_002": {
        "score": 37.11,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260602_220255",
        "cost_usd": 15.208125,
        "duration_seconds": 8111
      },
      "Material_003": {
        "score": 14.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260603_001836",
        "cost_usd": 8.03625,
        "duration_seconds": 4286
      },
      "Math_000": {
        "score": 22.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260603_094603",
        "cost_usd": 4.365,
        "duration_seconds": 2328
      },
      "Math_001": {
        "score": 24.1,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260603_102506",
        "cost_usd": 4.365,
        "duration_seconds": 2328
      },
      "Math_002": {
        "score": 9.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260603_110404",
        "cost_usd": 2.78625,
        "duration_seconds": 1486
      },
      "Math_003": {
        "score": 6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260603_112910",
        "cost_usd": 4.07625,
        "duration_seconds": 2174
      },
      "Neuroscience_000": {
        "score": 14.2,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260603_120527",
        "cost_usd": 5.053125,
        "duration_seconds": 2695
      },
      "Neuroscience_001": {
        "score": 18.5,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260603_133907",
        "cost_usd": 3.485625,
        "duration_seconds": 1859
      },
      "Neuroscience_002": {
        "score": 0.75,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260603_141028",
        "cost_usd": 4.786875,
        "duration_seconds": 2553
      },
      "Neuroscience_003": {
        "score": 12.3,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260603_152926",
        "cost_usd": 2.40375,
        "duration_seconds": 1282
      },
      "Physics_000": {
        "score": 24.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260603_155109",
        "cost_usd": 1.7475,
        "duration_seconds": 932
      },
      "Physics_001": {
        "score": 12.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260603_160705",
        "cost_usd": 3.571875,
        "duration_seconds": 1905
      },
      "Physics_002": {
        "score": 47.4,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260603_163907",
        "cost_usd": 6.51,
        "duration_seconds": 3472
      },
      "Physics_003": {
        "score": 55.6,
        "model": "gpt-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260603_173720",
        "cost_usd": 3.024375,
        "duration_seconds": 1613
      }
    },
    "InnoClaw": {
      "Astronomy_000": {
        "score": 43.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_000_20260724_032304",
        "cost_usd": 3.9225,
        "duration_seconds": 1046
      },
      "Astronomy_001": {
        "score": 39,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_001_20260725_153429",
        "cost_usd": 2.73,
        "duration_seconds": 728
      },
      "Astronomy_002": {
        "score": 30.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_002_20260727_200918",
        "cost_usd": 5.61,
        "duration_seconds": 1496
      },
      "Astronomy_003": {
        "score": 53.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_003_20260727_063154",
        "cost_usd": 1.75875,
        "duration_seconds": 469
      },
      "Chemistry_000": {
        "score": 19.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_000_20260724_032303",
        "cost_usd": 7.23375,
        "duration_seconds": 1929
      },
      "Chemistry_001": {
        "score": 11.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_001_20260725_153350",
        "cost_usd": 4.9875,
        "duration_seconds": 1330
      },
      "Chemistry_002": {
        "score": 17.65,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_002_20260726_191910",
        "cost_usd": 1.69125,
        "duration_seconds": 451
      },
      "Chemistry_003": {
        "score": 23.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_003_20260727_063154",
        "cost_usd": 11.175,
        "duration_seconds": 2980
      },
      "Earth_000": {
        "score": 30.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_000_20260724_032302",
        "cost_usd": 4.48875,
        "duration_seconds": 1197
      },
      "Earth_001": {
        "score": 43.94,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_001_20260727_200916",
        "cost_usd": 2.64375,
        "duration_seconds": 705
      },
      "Earth_002": {
        "score": 26.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_002_20260726_191912",
        "cost_usd": 4.32,
        "duration_seconds": 1152
      },
      "Earth_003": {
        "score": 9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_003_20260727_100323",
        "cost_usd": 2.0175,
        "duration_seconds": 538
      },
      "Energy_000": {
        "score": 19.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_000_20260724_041119",
        "cost_usd": 79.27875,
        "duration_seconds": 21141
      },
      "Energy_001": {
        "score": 39.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_001_20260725_160618",
        "cost_usd": 5.56875,
        "duration_seconds": 1485
      },
      "Energy_002": {
        "score": 41.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_002_20260726_191912",
        "cost_usd": 8.985,
        "duration_seconds": 2396
      },
      "Energy_003": {
        "score": 21.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_003_20260727_063154",
        "cost_usd": 2.8575,
        "duration_seconds": 762
      },
      "Information_000": {
        "score": 20.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_000_20260728_194057",
        "cost_usd": 2.37,
        "duration_seconds": 632
      },
      "Information_001": {
        "score": 10.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_001_20260725_163104",
        "cost_usd": 3.72,
        "duration_seconds": 992
      },
      "Information_002": {
        "score": 49.1,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_002_20260726_191911",
        "cost_usd": 5.71875,
        "duration_seconds": 1525
      },
      "Information_003": {
        "score": 16.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_003_20260727_144636",
        "cost_usd": 9.9825,
        "duration_seconds": 2662
      },
      "Life_000": {
        "score": 12.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_000_20260724_032303",
        "cost_usd": 8.295,
        "duration_seconds": 2212
      },
      "Life_001": {
        "score": 27.9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_001_20260727_202239",
        "cost_usd": 3.4725,
        "duration_seconds": 926
      },
      "Life_002": {
        "score": 12.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_002_20260726_191915",
        "cost_usd": 5.595,
        "duration_seconds": 1492
      },
      "Life_003": {
        "score": 45.9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_003_20260728_134628",
        "cost_usd": 2.93625,
        "duration_seconds": 783
      },
      "Material_000": {
        "score": 34.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_000_20260724_032302",
        "cost_usd": 14.1,
        "duration_seconds": 3760
      },
      "Material_001": {
        "score": 37,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_001_20260725_153432",
        "cost_usd": 3.04875,
        "duration_seconds": 813
      },
      "Material_002": {
        "score": 32.46,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_002_20260726_191916",
        "cost_usd": 3.76125,
        "duration_seconds": 1003
      },
      "Material_003": {
        "score": 25.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_003_20260727_063155",
        "cost_usd": 6.30375,
        "duration_seconds": 1681
      },
      "Math_000": {
        "score": 32.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_000_20260724_121321",
        "cost_usd": 7.93125,
        "duration_seconds": 2115
      },
      "Math_001": {
        "score": 46.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_001_20260725_164243",
        "cost_usd": 7.2525,
        "duration_seconds": 1934
      },
      "Math_002": {
        "score": 19.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_002_20260726_223602",
        "cost_usd": 5.38875,
        "duration_seconds": 1437
      },
      "Math_003": {
        "score": 14,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_003_20260727_144635",
        "cost_usd": 8.7225,
        "duration_seconds": 2326
      },
      "Neuroscience_000": {
        "score": 12.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_000_20260724_120733",
        "cost_usd": 9.68625,
        "duration_seconds": 2583
      },
      "Neuroscience_001": {
        "score": 6.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_001_20260725_153433",
        "cost_usd": 7.0875,
        "duration_seconds": 1890
      },
      "Neuroscience_002": {
        "score": 12.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_002_20260726_230005",
        "cost_usd": 5.025,
        "duration_seconds": 1340
      },
      "Neuroscience_003": {
        "score": 33.75,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_003_20260727_063155",
        "cost_usd": 3.885,
        "duration_seconds": 1036
      },
      "Physics_000": {
        "score": 38.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_000_20260805_161215",
        "cost_usd": 2.53125,
        "duration_seconds": 675
      },
      "Physics_001": {
        "score": 40.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_001_20260804_111234",
        "cost_usd": 2.7525,
        "duration_seconds": 734
      },
      "Physics_002": {
        "score": 47.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_002_20260726_232225",
        "cost_usd": 2.43,
        "duration_seconds": 648
      },
      "Physics_003": {
        "score": 54.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_003_20260805_151715",
        "cost_usd": 2.91375,
        "duration_seconds": 777
      }
    },
    "InnoClaw (2.0)": {
      "Astronomy_000": {
        "score": 43.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_000_20260724_032304_innoclaw2",
        "cost_usd": 3.9225,
        "duration_seconds": 1046
      },
      "Astronomy_001": {
        "score": 39,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_001_20260725_153429_innoclaw2",
        "cost_usd": 2.73,
        "duration_seconds": 728
      },
      "Astronomy_002": {
        "score": 30.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_002_20260727_200918_innoclaw2",
        "cost_usd": 5.61,
        "duration_seconds": 1496
      },
      "Astronomy_003": {
        "score": 53.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_003_20260727_063154_innoclaw2",
        "cost_usd": 1.75875,
        "duration_seconds": 469
      },
      "Chemistry_000": {
        "score": 31.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_000_20260902_105842_innoclaw2",
        "cost_usd": 6.5025,
        "duration_seconds": 1734
      },
      "Chemistry_001": {
        "score": 18.15,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_001_20260828_025831_innoclaw2",
        "cost_usd": 5.65125,
        "duration_seconds": 1507
      },
      "Chemistry_002": {
        "score": 34.15,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_002_20260829_220805_innoclaw2",
        "cost_usd": 4.7925,
        "duration_seconds": 1278
      },
      "Chemistry_003": {
        "score": 46.9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_003_20260826_142823_innoclaw2",
        "cost_usd": 21.48,
        "duration_seconds": 5728
      },
      "Earth_000": {
        "score": 30.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_000_20260724_032302_innoclaw2",
        "cost_usd": 4.48875,
        "duration_seconds": 1197
      },
      "Earth_001": {
        "score": 43.94,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_001_20260727_200916_innoclaw2",
        "cost_usd": 2.64375,
        "duration_seconds": 705
      },
      "Earth_002": {
        "score": 26.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_002_20260726_191912_innoclaw2",
        "cost_usd": 4.32,
        "duration_seconds": 1152
      },
      "Earth_003": {
        "score": 9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_003_20260727_100323_innoclaw2",
        "cost_usd": 2.0175,
        "duration_seconds": 538
      },
      "Energy_000": {
        "score": 19.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_000_20260724_041119_innoclaw2",
        "cost_usd": 79.27875,
        "duration_seconds": 21141
      },
      "Energy_001": {
        "score": 39.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_001_20260725_160618_innoclaw2",
        "cost_usd": 5.56875,
        "duration_seconds": 1485
      },
      "Energy_002": {
        "score": 41.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_002_20260726_191912_innoclaw2",
        "cost_usd": 8.985,
        "duration_seconds": 2396
      },
      "Energy_003": {
        "score": 21.2,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_003_20260727_063154_innoclaw2",
        "cost_usd": 2.8575,
        "duration_seconds": 762
      },
      "Information_000": {
        "score": 45.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_000_20260905_154941_innoclaw2",
        "cost_usd": 1.5675,
        "duration_seconds": 418
      },
      "Information_001": {
        "score": 10.4,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_001_20260725_163104_innoclaw2",
        "cost_usd": 3.72,
        "duration_seconds": 992
      },
      "Information_002": {
        "score": 58,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_002_20260905_154941_innoclaw2",
        "cost_usd": 2.505,
        "duration_seconds": 668
      },
      "Information_003": {
        "score": 30.05,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_003_20260905_161128_innoclaw2",
        "cost_usd": 15.75,
        "duration_seconds": 4200
      },
      "Life_000": {
        "score": 42.85,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_000_20260905_161129_innoclaw2",
        "cost_usd": 16.24125,
        "duration_seconds": 4331
      },
      "Life_001": {
        "score": 30.1,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_001_20260905_161129_innoclaw2",
        "cost_usd": 3.48375,
        "duration_seconds": 929
      },
      "Life_002": {
        "score": 12.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_002_20260726_191915_innoclaw2",
        "cost_usd": 5.595,
        "duration_seconds": 1492
      },
      "Life_003": {
        "score": 45.9,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_003_20260728_134628_innoclaw2",
        "cost_usd": 2.93625,
        "duration_seconds": 783
      },
      "Material_000": {
        "score": 34.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_000_20260724_032302_innoclaw2",
        "cost_usd": 14.1,
        "duration_seconds": 3760
      },
      "Material_001": {
        "score": 37,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_001_20260725_153432_innoclaw2",
        "cost_usd": 3.04875,
        "duration_seconds": 813
      },
      "Material_002": {
        "score": 32.46,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_002_20260726_191916_innoclaw2",
        "cost_usd": 3.76125,
        "duration_seconds": 1003
      },
      "Material_003": {
        "score": 25.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_003_20260727_063155_innoclaw2",
        "cost_usd": 6.30375,
        "duration_seconds": 1681
      },
      "Math_000": {
        "score": 32.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_000_20260905_172340_innoclaw2",
        "cost_usd": 8.55375,
        "duration_seconds": 2281
      },
      "Math_001": {
        "score": 50.7,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_001_20260905_180142_innoclaw2",
        "cost_usd": 3.68625,
        "duration_seconds": 983
      },
      "Math_002": {
        "score": 28,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_002_20260905_180142_innoclaw2",
        "cost_usd": 1.44375,
        "duration_seconds": 385
      },
      "Math_003": {
        "score": 25.75,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_003_20260905_180142_innoclaw2",
        "cost_usd": 1.54125,
        "duration_seconds": 411
      },
      "Neuroscience_000": {
        "score": 25.8,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_000_20260903_132737_innoclaw2",
        "cost_usd": 15.4575,
        "duration_seconds": 4122
      },
      "Neuroscience_001": {
        "score": 39.5,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_001_20260903_174751_innoclaw2",
        "cost_usd": 6.97875,
        "duration_seconds": 1861
      },
      "Neuroscience_002": {
        "score": 38.55,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_002_20260903_174815_innoclaw2",
        "cost_usd": 50.71125,
        "duration_seconds": 13523
      },
      "Neuroscience_003": {
        "score": 39.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_003_20260903_132941_innoclaw2",
        "cost_usd": 16.2825,
        "duration_seconds": 4342
      },
      "Physics_000": {
        "score": 38.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_000_20260805_161215_innoclaw2",
        "cost_usd": 2.53125,
        "duration_seconds": 675
      },
      "Physics_001": {
        "score": 40.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_001_20260804_111234_innoclaw2",
        "cost_usd": 2.7525,
        "duration_seconds": 734
      },
      "Physics_002": {
        "score": 47.3,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_002_20260726_232225_innoclaw2",
        "cost_usd": 2.43,
        "duration_seconds": 648
      },
      "Physics_003": {
        "score": 54.6,
        "model": "gpt-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_003_20260805_151715_innoclaw2",
        "cost_usd": 2.91375,
        "duration_seconds": 777
      }
    },
    "Ligase": {
      "Astronomy_000": {
        "score": 35,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Astronomy_000_20260831_022939_ee9573fd",
        "cost_usd": 9.285333,
        "duration_seconds": 3482
      },
      "Astronomy_001": {
        "score": 43.4,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Astronomy_001_20260831_022939_cd8ac22d",
        "cost_usd": 6.229333,
        "duration_seconds": 2336
      },
      "Astronomy_002": {
        "score": 23.5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Astronomy_002_20260831_022939_79491e49",
        "cost_usd": 4.328,
        "duration_seconds": 1623
      },
      "Astronomy_003": {
        "score": 47.5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Astronomy_003_20260831_022939_39356b92",
        "cost_usd": 11.858667,
        "duration_seconds": 4447
      },
      "Chemistry_000": {
        "score": 30.4,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Chemistry_000_20260831_022939_f1f5b38e",
        "cost_usd": 8.08,
        "duration_seconds": 3030
      },
      "Chemistry_001": {
        "score": 22.7,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Chemistry_001_20260831_022939_3bf68313",
        "cost_usd": 11.637333,
        "duration_seconds": 4364
      },
      "Chemistry_002": {
        "score": 36.85,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Chemistry_002_20260831_022939_6d585bd3",
        "cost_usd": 5.133333,
        "duration_seconds": 1925
      },
      "Chemistry_003": {
        "score": 1.5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Chemistry_003_20260831_022939_fe063b60",
        "cost_usd": 6.656,
        "duration_seconds": 2496
      },
      "Earth_000": {
        "score": 33,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Earth_000_20260831_022939_4fbf7aeb",
        "cost_usd": 3.677333,
        "duration_seconds": 1379
      },
      "Earth_001": {
        "score": 39.74,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Earth_001_20260831_022939_669d52d6",
        "cost_usd": 4.258667,
        "duration_seconds": 1597
      },
      "Earth_002": {
        "score": 32.3,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Earth_002_20260831_022939_b5d6a42f",
        "cost_usd": 10.618667,
        "duration_seconds": 3982
      },
      "Earth_003": {
        "score": 32,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Earth_003_20260831_022939_26c4f07e",
        "cost_usd": 3.954667,
        "duration_seconds": 1483
      },
      "Energy_000": {
        "score": 24.5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Energy_000_20260831_022939_c0751b5d",
        "cost_usd": 13.202667,
        "duration_seconds": 4951
      },
      "Energy_001": {
        "score": 26.5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Energy_001_20260831_022939_7a66cb73",
        "cost_usd": 5.042667,
        "duration_seconds": 1891
      },
      "Energy_002": {
        "score": 42.85,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Energy_002_20260831_022939_1316c624",
        "cost_usd": 4.656,
        "duration_seconds": 1746
      },
      "Energy_003": {
        "score": 25.9,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Energy_003_20260831_022939_82ab9cda",
        "cost_usd": 5.389333,
        "duration_seconds": 2021
      },
      "Information_000": {
        "score": 33,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Information_000_20260831_022939_dc32f113",
        "cost_usd": 8.92,
        "duration_seconds": 3345
      },
      "Information_001": {
        "score": 35.2,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Information_001_20260831_022939_f78f90cd",
        "cost_usd": 9.901333,
        "duration_seconds": 3713
      },
      "Information_002": {
        "score": 47.1,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Information_002_20260831_022939_4fd33dd4",
        "cost_usd": 5.573333,
        "duration_seconds": 2090
      },
      "Information_003": {
        "score": 44.9,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Information_003_20260831_022939_a966dce6",
        "cost_usd": 4.976,
        "duration_seconds": 1866
      },
      "Life_000": {
        "score": 35.1,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Life_000_20260831_022939_08844a22",
        "cost_usd": 4.237333,
        "duration_seconds": 1589
      },
      "Life_001": {
        "score": 43.4,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Life_001_20260831_022939_d077d37f",
        "cost_usd": 7.493333,
        "duration_seconds": 2810
      },
      "Life_002": {
        "score": 20.6,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Life_002_20260831_022939_a87fbac0",
        "cost_usd": 6.013333,
        "duration_seconds": 2255
      },
      "Life_003": {
        "score": 31,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Life_003_20260831_022939_0e0f0d88",
        "cost_usd": 11.578667,
        "duration_seconds": 4342
      },
      "Material_000": {
        "score": 26,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Material_000_20260831_022939_0a9cdfbb",
        "cost_usd": 8.101333,
        "duration_seconds": 3038
      },
      "Material_001": {
        "score": 19.95,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Material_001_20260831_022939_ca6f47eb",
        "cost_usd": 11.194667,
        "duration_seconds": 4198
      },
      "Material_002": {
        "score": 47.01,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Material_002_20260831_022939_31d4b01e",
        "cost_usd": 9.986667,
        "duration_seconds": 3745
      },
      "Material_003": {
        "score": 47.25,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Material_003_20260831_022939_b955eb75",
        "cost_usd": 7.224,
        "duration_seconds": 2709
      },
      "Math_000": {
        "score": 31,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Math_000_20260831_022939_6c859ec7",
        "cost_usd": 5.250667,
        "duration_seconds": 1969
      },
      "Math_001": {
        "score": 46.3,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Math_001_20260831_022939_4e959d5f",
        "cost_usd": 5.173333,
        "duration_seconds": 1940
      },
      "Math_002": {
        "score": 42.6,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Math_002_20260831_022939_bda2abee",
        "cost_usd": 9.253333,
        "duration_seconds": 3470
      },
      "Math_003": {
        "score": 38.75,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Math_003_20260831_022939_0099b1b6",
        "cost_usd": 9.282667,
        "duration_seconds": 3481
      },
      "Neuroscience_000": {
        "score": 5,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Neuroscience_000_20260831_022939_5f088b8e",
        "cost_usd": 12.722667,
        "duration_seconds": 4771
      },
      "Neuroscience_001": {
        "score": 49.55,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Neuroscience_001_20260831_022939_e07a8987",
        "cost_usd": 19.2,
        "duration_seconds": 7200
      },
      "Neuroscience_002": {
        "score": 42.65,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Neuroscience_002_20260831_022939_1f657935",
        "cost_usd": 3.272,
        "duration_seconds": 1227
      },
      "Neuroscience_003": {
        "score": 44.15,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Neuroscience_003_20260831_022939_2750fe84",
        "cost_usd": 3.213333,
        "duration_seconds": 1205
      },
      "Physics_000": {
        "score": 35.3,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Physics_000_20260831_022939_e4bbaa2d",
        "cost_usd": 9.48,
        "duration_seconds": 3555
      },
      "Physics_001": {
        "score": 35.1,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Physics_001_20260831_022939_64c10709",
        "cost_usd": 10.077333,
        "duration_seconds": 3779
      },
      "Physics_002": {
        "score": 47.1,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Physics_002_20260831_022939_d768a17c",
        "cost_usd": 4.925333,
        "duration_seconds": 1847
      },
      "Physics_003": {
        "score": 46.4,
        "model": "gpt-5.6-sol + grd-king + grd-jin",
        "model_display": "GPT-5.6-Sol",
        "run_id": "cli_Physics_003_20260831_022939_347d0cf8",
        "cost_usd": 5.013333,
        "duration_seconds": 1880
      }
    },
    "Open Science": {
      "Astronomy_000": {
        "score": 18.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_000_20260708_141803",
        "cost_usd": 4.856667,
        "duration_seconds": 1457
      },
      "Astronomy_001": {
        "score": 18,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_001_20260708_150307",
        "cost_usd": 1.596667,
        "duration_seconds": 479
      },
      "Astronomy_002": {
        "score": 35.3,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_002_20260708_144253",
        "cost_usd": 2.45,
        "duration_seconds": 735
      },
      "Astronomy_003": {
        "score": 45.6,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_003_20260708_145508",
        "cost_usd": 0.873333,
        "duration_seconds": 262
      },
      "Chemistry_001": {
        "score": 3.75,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Chemistry_001_20260708_163144",
        "cost_usd": 5.796667,
        "duration_seconds": 1739
      },
      "Chemistry_002": {
        "score": 15.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Chemistry_002_20260708_170057",
        "cost_usd": 6.246667,
        "duration_seconds": 1874
      },
      "Earth_000": {
        "score": 12.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_000_20260708_131953",
        "cost_usd": 3.08,
        "duration_seconds": 924
      },
      "Earth_001": {
        "score": 37.57,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_001_20260708_170025",
        "cost_usd": 1.033333,
        "duration_seconds": 310
      },
      "Earth_002": {
        "score": 26.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_002_20260708_180031",
        "cost_usd": 1.883333,
        "duration_seconds": 565
      },
      "Earth_003": {
        "score": 1.4,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_003_20260708_181010",
        "cost_usd": 1.45,
        "duration_seconds": 435
      },
      "Energy_000": {
        "score": 4.4,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_000_20260708_181736",
        "cost_usd": 3.216667,
        "duration_seconds": 965
      },
      "Energy_001": {
        "score": 18.7,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_001_20260708_183349",
        "cost_usd": 1.663333,
        "duration_seconds": 499
      },
      "Energy_002": {
        "score": 38.45,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_002_20260708_184215",
        "cost_usd": 1.49,
        "duration_seconds": 447
      },
      "Energy_003": {
        "score": 12.1,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_003_20260708_184954",
        "cost_usd": 1.893333,
        "duration_seconds": 568
      },
      "Information_000": {
        "score": 39.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_000_20260708_185934",
        "cost_usd": 3.483333,
        "duration_seconds": 1045
      },
      "Information_001": {
        "score": 7,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_001_20260708_191705",
        "cost_usd": 5.55,
        "duration_seconds": 1665
      },
      "Information_002": {
        "score": 23.6,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_002_20260708_194503",
        "cost_usd": 1.37,
        "duration_seconds": 411
      },
      "Information_003": {
        "score": 11.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_003_20260708_195202",
        "cost_usd": 7.466667,
        "duration_seconds": 2240
      },
      "Life_000": {
        "score": 11.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_000_20260708_202931",
        "cost_usd": 2.336667,
        "duration_seconds": 701
      },
      "Life_001": {
        "score": 10.15,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_001_20260708_204124",
        "cost_usd": 1.323333,
        "duration_seconds": 397
      },
      "Life_003": {
        "score": 28.6,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_003_20260708_234848",
        "cost_usd": 1.23,
        "duration_seconds": 369
      },
      "Material_000": {
        "score": 28,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_000_20260708_235507",
        "cost_usd": 3.8,
        "duration_seconds": 1140
      },
      "Material_001": {
        "score": 24.7,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_001_20260709_001416",
        "cost_usd": 5.41,
        "duration_seconds": 1623
      },
      "Material_003": {
        "score": 24.6,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_003_20260709_034202",
        "cost_usd": 5.206667,
        "duration_seconds": 1562
      },
      "Math_000": {
        "score": 32.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_000_20260709_040918",
        "cost_usd": 3.61,
        "duration_seconds": 1083
      },
      "Math_001": {
        "score": 47.7,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_001_20260709_042729",
        "cost_usd": 6.41,
        "duration_seconds": 1923
      },
      "Math_002": {
        "score": 12.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_002_20260709_045940",
        "cost_usd": 12.683333,
        "duration_seconds": 3805
      },
      "Math_003": {
        "score": 16,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_003_20260709_060320",
        "cost_usd": 4.033333,
        "duration_seconds": 1210
      },
      "Neuroscience_000": {
        "score": 6,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_000_20260709_062333",
        "cost_usd": 1.643333,
        "duration_seconds": 493
      },
      "Neuroscience_001": {
        "score": 22.25,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_001_20260709_063155",
        "cost_usd": 8.166667,
        "duration_seconds": 2450
      },
      "Neuroscience_002": {
        "score": 7,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_002_20260709_071257",
        "cost_usd": 3.26,
        "duration_seconds": 978
      },
      "Neuroscience_003": {
        "score": 18.15,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_003_20260709_072925",
        "cost_usd": 1.856667,
        "duration_seconds": 557
      },
      "Physics_000": {
        "score": 31.5,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_000_20260709_073855",
        "cost_usd": 2.256667,
        "duration_seconds": 677
      },
      "Physics_001": {
        "score": 49,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_001_20260709_075019",
        "cost_usd": 2.31,
        "duration_seconds": 693
      },
      "Physics_002": {
        "score": 31.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_002_20260709_080200",
        "cost_usd": 1.403333,
        "duration_seconds": 421
      },
      "Physics_003": {
        "score": 47.8,
        "model": "claude-opus-4.8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_003_20260709_080916",
        "cost_usd": 1.356667,
        "duration_seconds": 407
      }
    },
    "Qiushi Engine": {
      "Astronomy_000": {
        "score": 46.5,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Astronomy_000_imported_20260904",
        "cost_usd": 6.786,
        "duration_seconds": 9360
      },
      "Astronomy_001": {
        "score": 48,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Astronomy_001_imported_20260904",
        "cost_usd": 7.656,
        "duration_seconds": 10560
      },
      "Astronomy_002": {
        "score": 28.4,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Astronomy_002_imported_20260904",
        "cost_usd": 6.4815,
        "duration_seconds": 8940
      },
      "Astronomy_003": {
        "score": 48.3,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Astronomy_003_imported_deliverables_20260904",
        "cost_usd": 1.5225,
        "duration_seconds": 2100
      },
      "Chemistry_000": {
        "score": 39.8,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Chemistry_000_imported",
        "cost_usd": 7.1775,
        "duration_seconds": 9900
      },
      "Chemistry_001": {
        "score": 18.75,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Chemistry_001_new_submission",
        "cost_usd": 3.915,
        "duration_seconds": 5400
      },
      "Chemistry_002": {
        "score": 39.15,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Chemistry_002_imported",
        "cost_usd": 3.219,
        "duration_seconds": 4440
      },
      "Chemistry_003": {
        "score": 24.9,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Chemistry_003_imported",
        "cost_usd": 31.581,
        "duration_seconds": 43560
      },
      "Earth_000": {
        "score": 48.8,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Earth_000_imported",
        "cost_usd": 5.0895,
        "duration_seconds": 7020
      },
      "Earth_001": {
        "score": 48,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Earth_001_imported",
        "cost_usd": 0.7395,
        "duration_seconds": 1020
      },
      "Earth_002": {
        "score": 47.2,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Earth_002_imported",
        "cost_usd": 3.915,
        "duration_seconds": 5400
      },
      "Earth_003": {
        "score": 33.4,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Earth_003_imported",
        "cost_usd": 3.219,
        "duration_seconds": 4440
      },
      "Energy_000": {
        "score": 31.9,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Energy_000_imported",
        "cost_usd": 1.827,
        "duration_seconds": 2520
      },
      "Energy_001": {
        "score": 43.5,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Energy_001_imported",
        "cost_usd": 1.479,
        "duration_seconds": 2040
      },
      "Energy_002": {
        "score": 45.9,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Energy_002_imported",
        "cost_usd": 1.392,
        "duration_seconds": 1920
      },
      "Energy_003": {
        "score": 61.4,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Energy_003_imported",
        "cost_usd": 4.3935,
        "duration_seconds": 6060
      },
      "Information_000": {
        "score": 52.9,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Information_000_imported",
        "cost_usd": 11.397,
        "duration_seconds": 15720
      },
      "Information_001": {
        "score": 38,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Information_001_imported_20260908",
        "cost_usd": 21.402,
        "duration_seconds": 29520
      },
      "Information_002": {
        "score": 32.6,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Information_002_imported_20260906",
        "cost_usd": 2.9145,
        "duration_seconds": 4020
      },
      "Information_003": {
        "score": 35.75,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Information_003_imported_20260908",
        "cost_usd": 20.706,
        "duration_seconds": 28560
      },
      "Life_000": {
        "score": 43.6,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Life_000_imported_20260906",
        "cost_usd": 3.7845,
        "duration_seconds": 5220
      },
      "Life_001": {
        "score": 19.5,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Life_001_imported_20260907",
        "cost_usd": 1.566,
        "duration_seconds": 2160
      },
      "Life_002": {
        "score": 11.8,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Life_002_imported_20260906",
        "cost_usd": 2.958,
        "duration_seconds": 4080
      },
      "Life_003": {
        "score": 46.1,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Life_003_imported_20260906",
        "cost_usd": 1.044,
        "duration_seconds": 1440
      },
      "Material_000": {
        "score": 25.7,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Material_000_imported_20260906",
        "cost_usd": 1.827,
        "duration_seconds": 2520
      },
      "Material_001": {
        "score": 53.45,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Material_001_imported_20260906",
        "cost_usd": 10.3095,
        "duration_seconds": 14220
      },
      "Material_002": {
        "score": 46.04,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Material_002_imported_20260907",
        "cost_usd": 15.051,
        "duration_seconds": 20760
      },
      "Material_003": {
        "score": 39.6,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Material_003_imported_20260907",
        "cost_usd": 13.1805,
        "duration_seconds": 18180
      },
      "Math_000": {
        "score": 33.55,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Math_000_imported_20260906",
        "cost_usd": 5.6985,
        "duration_seconds": 7860
      },
      "Math_001": {
        "score": 57.1,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Math_001_imported_20260908",
        "cost_usd": 8.1345,
        "duration_seconds": 11220
      },
      "Math_002": {
        "score": 28,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Math_002_imported_20260908",
        "cost_usd": 15.66,
        "duration_seconds": 21600
      },
      "Math_003": {
        "score": 14,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Math_003_imported_20260907",
        "cost_usd": 8.6565,
        "duration_seconds": 11940
      },
      "Neuroscience_000": {
        "score": 11.4,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Neuroscience_000_imported_20260907",
        "cost_usd": 6.264,
        "duration_seconds": 8640
      },
      "Neuroscience_001": {
        "score": 34.75,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Neuroscience_001_imported_20260907",
        "cost_usd": 3.132,
        "duration_seconds": 4320
      },
      "Neuroscience_002": {
        "score": 33.85,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Neuroscience_002_imported_20260907",
        "cost_usd": 18.3135,
        "duration_seconds": 25260
      },
      "Neuroscience_003": {
        "score": 50.3,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Neuroscience_003_imported_20260907",
        "cost_usd": 13.572,
        "duration_seconds": 18720
      },
      "Physics_000": {
        "score": 53,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Physics_000_imported_20260907",
        "cost_usd": 15.1815,
        "duration_seconds": 20940
      },
      "Physics_001": {
        "score": 41.65,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Physics_001_imported_20260907",
        "cost_usd": 10.0485,
        "duration_seconds": 13860
      },
      "Physics_002": {
        "score": 40.2,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Physics_002_imported_20260907",
        "cost_usd": 1.7835,
        "duration_seconds": 2460
      },
      "Physics_003": {
        "score": 47.9,
        "model": "deepseek-v4-pro-preview",
        "model_display": "DeepSeek-V4-Pro-Preview",
        "run_id": "Physics_003_imported_20260907",
        "cost_usd": 2.3925,
        "duration_seconds": 3300
      }
    },
    "ResearchHarness (Claude-Opus-4.6)": {
      "Astronomy_000": {
        "score": 33.1,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_000_20260416_171148",
        "cost_usd": 3.866667,
        "duration_seconds": 1160
      },
      "Astronomy_002": {
        "score": 24.5,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_002_20260415_121118",
        "cost_usd": 8.526667,
        "duration_seconds": 2558
      },
      "Astronomy_003": {
        "score": 47.6,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Astronomy_003_20260415_125416",
        "cost_usd": 1.926667,
        "duration_seconds": 578
      },
      "Chemistry_000": {
        "score": 9.35,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_000_20260416_173125",
        "cost_usd": 6.55,
        "duration_seconds": 1965
      },
      "Chemistry_001": {
        "score": 9,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_001_20260415_134024",
        "cost_usd": 5.806667,
        "duration_seconds": 1742
      },
      "Chemistry_002": {
        "score": 3.4,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_002_20260416_175027",
        "cost_usd": 11.076667,
        "duration_seconds": 3323
      },
      "Chemistry_003": {
        "score": 7.2,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Chemistry_003_20260416_180425",
        "cost_usd": 3.103333,
        "duration_seconds": 931
      },
      "Earth_000": {
        "score": 21.5,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_000_20260417_110902",
        "cost_usd": 2.01,
        "duration_seconds": 603
      },
      "Earth_001": {
        "score": 40.94,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_001_20260417_103256",
        "cost_usd": 1.42,
        "duration_seconds": 426
      },
      "Earth_002": {
        "score": 28.8,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Earth_002_20260417_110902",
        "cost_usd": 2.913333,
        "duration_seconds": 874
      },
      "Energy_000": {
        "score": 12.3,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_000_20260416_182016",
        "cost_usd": 7.18,
        "duration_seconds": 2154
      },
      "Energy_001": {
        "score": 25.1,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_001_20260416_184602",
        "cost_usd": 2.546667,
        "duration_seconds": 764
      },
      "Energy_002": {
        "score": 42.45,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_002_20260416_185623",
        "cost_usd": 2.443333,
        "duration_seconds": 733
      },
      "Energy_003": {
        "score": 24,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Energy_003_20260416_185858",
        "cost_usd": 1.72,
        "duration_seconds": 516
      },
      "Information_000": {
        "score": 23.2,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_000_20260416_190754",
        "cost_usd": 8.366667,
        "duration_seconds": 2510
      },
      "Information_001": {
        "score": 3.6,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_001_20260416_190849",
        "cost_usd": 7.48,
        "duration_seconds": 2244
      },
      "Information_002": {
        "score": 20.1,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_002_20260416_194642",
        "cost_usd": 1.686667,
        "duration_seconds": 506
      },
      "Information_003": {
        "score": 4.35,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Information_003_20260416_195002",
        "cost_usd": 28.233333,
        "duration_seconds": 8470
      },
      "Life_000": {
        "score": 9.35,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_000_20260416_195517",
        "cost_usd": 2.43,
        "duration_seconds": 729
      },
      "Life_001": {
        "score": 3.6,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_001_20260416_200743",
        "cost_usd": 1.67,
        "duration_seconds": 501
      },
      "Life_002": {
        "score": 5.7,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_002_20260416_201623",
        "cost_usd": 2.536667,
        "duration_seconds": 761
      },
      "Life_003": {
        "score": 32.1,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Life_003_20260416_202913",
        "cost_usd": 2.43,
        "duration_seconds": 729
      },
      "Material_000": {
        "score": 25.1,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_000_20260416_204143",
        "cost_usd": 18.8,
        "duration_seconds": 5640
      },
      "Material_001": {
        "score": 1.75,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_001_20260416_221126",
        "cost_usd": 11.526667,
        "duration_seconds": 3458
      },
      "Material_002": {
        "score": 39.08,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_002_20260416_221556",
        "cost_usd": 27.876667,
        "duration_seconds": 8363
      },
      "Material_003": {
        "score": 14,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Material_003_20260416_230923",
        "cost_usd": 10.983333,
        "duration_seconds": 3295
      },
      "Math_000": {
        "score": 23,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_000_20260417_000449",
        "cost_usd": 4.15,
        "duration_seconds": 1245
      },
      "Math_001": {
        "score": 34.3,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_001_20260417_002550",
        "cost_usd": 2.943333,
        "duration_seconds": 883
      },
      "Math_002": {
        "score": 20.5,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_002_20260417_112354",
        "cost_usd": 6.346667,
        "duration_seconds": 1904
      },
      "Math_003": {
        "score": 11.75,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Math_003_20260417_003641",
        "cost_usd": 1.856667,
        "duration_seconds": 557
      },
      "Neuroscience_000": {
        "score": 10.4,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_000_20260417_004047",
        "cost_usd": 3.993333,
        "duration_seconds": 1198
      },
      "Neuroscience_001": {
        "score": 2.7,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_001_20260417_004607",
        "cost_usd": 2.296667,
        "duration_seconds": 689
      },
      "Neuroscience_002": {
        "score": 0.75,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_002_20260417_005802",
        "cost_usd": 3.286667,
        "duration_seconds": 986
      },
      "Neuroscience_003": {
        "score": 15.55,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Neuroscience_003_20260417_010102",
        "cost_usd": 2.27,
        "duration_seconds": 681
      },
      "Physics_000": {
        "score": 26.8,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_000_20260417_011243",
        "cost_usd": 3.136667,
        "duration_seconds": 941
      },
      "Physics_002": {
        "score": 32.4,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_002_20260417_012839",
        "cost_usd": 1.65,
        "duration_seconds": 495
      },
      "Physics_003": {
        "score": 45.8,
        "model": "Claude-Opus-4.6",
        "model_display": "Claude-Opus-4.6",
        "run_id": "Physics_003_20260417_013739",
        "cost_usd": 6.716667,
        "duration_seconds": 2015
      }
    },
    "ResearchHarness (Claude-Opus-4.7)": {
      "Astronomy_000": {
        "score": 25.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Astronomy_000_20260427_114915",
        "cost_usd": 2.493333,
        "duration_seconds": 748
      },
      "Astronomy_001": {
        "score": 26.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Astronomy_001_20260427_114915",
        "cost_usd": 1.57,
        "duration_seconds": 471
      },
      "Astronomy_002": {
        "score": 32,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Astronomy_002_20260427_115721",
        "cost_usd": 1.906667,
        "duration_seconds": 572
      },
      "Astronomy_003": {
        "score": 47.4,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Astronomy_003_20260427_120156",
        "cost_usd": 0.883333,
        "duration_seconds": 265
      },
      "Chemistry_001": {
        "score": 7.4,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Chemistry_001_20260427_120701",
        "cost_usd": 14.026667,
        "duration_seconds": 4208
      },
      "Chemistry_002": {
        "score": 1,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Chemistry_002_20260427_131724",
        "cost_usd": 13.253333,
        "duration_seconds": 3976
      },
      "Earth_000": {
        "score": 15.5,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Earth_000_20260427_143635",
        "cost_usd": 2.696667,
        "duration_seconds": 809
      },
      "Earth_001": {
        "score": 38.94,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Earth_001_20260427_145034",
        "cost_usd": 1.583333,
        "duration_seconds": 475
      },
      "Earth_002": {
        "score": 34,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Earth_002_20260427_145841",
        "cost_usd": 3.14,
        "duration_seconds": 942
      },
      "Earth_003": {
        "score": 1.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Earth_003_20260427_151445",
        "cost_usd": 2.636667,
        "duration_seconds": 791
      },
      "Energy_001": {
        "score": 17.1,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Energy_001_20260427_153415",
        "cost_usd": 3.043333,
        "duration_seconds": 913
      },
      "Energy_002": {
        "score": 41,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Energy_002_20260427_163143",
        "cost_usd": 3.88,
        "duration_seconds": 1164
      },
      "Energy_003": {
        "score": 11.5,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Energy_003_20260427_163143",
        "cost_usd": 1.75,
        "duration_seconds": 525
      },
      "Information_000": {
        "score": 0.8,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Information_000_20260427_164043",
        "cost_usd": 6.066667,
        "duration_seconds": 1820
      },
      "Information_001": {
        "score": 7.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Information_001_20260427_165119",
        "cost_usd": 14.616667,
        "duration_seconds": 4385
      },
      "Information_002": {
        "score": 32.3,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Information_002_20260427_171113",
        "cost_usd": 2.243333,
        "duration_seconds": 673
      },
      "Information_003": {
        "score": 14.9,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Information_003_20260427_172234",
        "cost_usd": 12.28,
        "duration_seconds": 3684
      },
      "Life_000": {
        "score": 5.45,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Life_000_20260427_180448",
        "cost_usd": 4.286667,
        "duration_seconds": 1286
      },
      "Life_001": {
        "score": 12.45,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Life_001_20260427_182412",
        "cost_usd": 1.166667,
        "duration_seconds": 350
      },
      "Life_002": {
        "score": 6.5,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Life_002_20260427_182632",
        "cost_usd": 5.666667,
        "duration_seconds": 1700
      },
      "Life_003": {
        "score": 26.9,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Life_003_20260427_183017",
        "cost_usd": 1.633333,
        "duration_seconds": 490
      },
      "Material_000": {
        "score": 21.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Material_000_20260427_183838",
        "cost_usd": 6.02,
        "duration_seconds": 1806
      },
      "Material_001": {
        "score": 18,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Material_001_20260427_185459",
        "cost_usd": 3.006667,
        "duration_seconds": 902
      },
      "Material_002": {
        "score": 35.81,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Material_002_20260427_190855",
        "cost_usd": 12.746667,
        "duration_seconds": 3824
      },
      "Material_003": {
        "score": 21.15,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Material_003_20260427_191010",
        "cost_usd": 15.596667,
        "duration_seconds": 4679
      },
      "Math_000": {
        "score": 22.95,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Math_000_20260427_201256",
        "cost_usd": 3.436667,
        "duration_seconds": 1031
      },
      "Math_001": {
        "score": 24.4,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Math_001_20260427_202826",
        "cost_usd": 2.366667,
        "duration_seconds": 710
      },
      "Math_002": {
        "score": 9.4,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Math_002_20260427_203016",
        "cost_usd": 10.353333,
        "duration_seconds": 3106
      },
      "Neuroscience_000": {
        "score": 10.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Neuroscience_000_20260427_211138",
        "cost_usd": 3.203333,
        "duration_seconds": 961
      },
      "Neuroscience_002": {
        "score": 3.75,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Neuroscience_002_20260427_212314",
        "cost_usd": 5.153333,
        "duration_seconds": 1546
      },
      "Neuroscience_003": {
        "score": 14.7,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Neuroscience_003_20260428_111256",
        "cost_usd": 3.4,
        "duration_seconds": 1020
      },
      "Physics_000": {
        "score": 14.2,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Physics_000_20260428_113010",
        "cost_usd": 2.216667,
        "duration_seconds": 665
      },
      "Physics_001": {
        "score": 39.95,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Physics_001_20260428_114127",
        "cost_usd": 4.13,
        "duration_seconds": 1239
      },
      "Physics_002": {
        "score": 38.6,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Physics_002_20260428_120221",
        "cost_usd": 1.72,
        "duration_seconds": 516
      },
      "Physics_003": {
        "score": 44.1,
        "model": "Claude-Opus-4.7",
        "model_display": "Claude-Opus-4.7",
        "run_id": "Physics_003_20260428_121142",
        "cost_usd": 2.976667,
        "duration_seconds": 893
      }
    },
    "ResearchHarness (Claude-Opus-4.8)": {
      "Astronomy_000": {
        "score": 33.1,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_000_20260601_203334",
        "cost_usd": 2.126667,
        "duration_seconds": 638
      },
      "Astronomy_001": {
        "score": 22.2,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_001_20260601_204426",
        "cost_usd": 1.643333,
        "duration_seconds": 493
      },
      "Astronomy_002": {
        "score": 34.6,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_002_20260601_205253",
        "cost_usd": 2.453333,
        "duration_seconds": 736
      },
      "Astronomy_003": {
        "score": 46.7,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Astronomy_003_20260601_210518",
        "cost_usd": 1.036667,
        "duration_seconds": 311
      },
      "Chemistry_000": {
        "score": 20.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Chemistry_000_20260601_211042",
        "cost_usd": 19.56,
        "duration_seconds": 5868
      },
      "Chemistry_002": {
        "score": 4.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Chemistry_002_20260601_231944",
        "cost_usd": 1.993333,
        "duration_seconds": 598
      },
      "Chemistry_003": {
        "score": 28.8,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Chemistry_003_20260601_233158",
        "cost_usd": 10.823333,
        "duration_seconds": 3247
      },
      "Earth_000": {
        "score": 13.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_000_20260602_002650",
        "cost_usd": 1.873333,
        "duration_seconds": 562
      },
      "Earth_001": {
        "score": 36.74,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_001_20260602_003849",
        "cost_usd": 1.116667,
        "duration_seconds": 335
      },
      "Earth_002": {
        "score": 29,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_002_20260602_004709",
        "cost_usd": 1.743333,
        "duration_seconds": 523
      },
      "Earth_003": {
        "score": 8.4,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Earth_003_20260602_005617",
        "cost_usd": 2.993333,
        "duration_seconds": 898
      },
      "Energy_000": {
        "score": 4.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_000_20260602_011501",
        "cost_usd": 4.523333,
        "duration_seconds": 1357
      },
      "Energy_001": {
        "score": 16.4,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_001_20260602_013904",
        "cost_usd": 2.123333,
        "duration_seconds": 637
      },
      "Energy_002": {
        "score": 41.95,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_002_20260602_015146",
        "cost_usd": 1.926667,
        "duration_seconds": 578
      },
      "Energy_003": {
        "score": 11,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Energy_003_20260602_020334",
        "cost_usd": 1.58,
        "duration_seconds": 474
      },
      "Information_000": {
        "score": 26.7,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_000_20260602_021341",
        "cost_usd": 2.35,
        "duration_seconds": 705
      },
      "Information_001": {
        "score": 8,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_001_20260602_022730",
        "cost_usd": 2.926667,
        "duration_seconds": 878
      },
      "Information_002": {
        "score": 31.4,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_002_20260602_024413",
        "cost_usd": 1.126667,
        "duration_seconds": 338
      },
      "Information_003": {
        "score": 14.9,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Information_003_20260602_025156",
        "cost_usd": 3.583333,
        "duration_seconds": 1075
      },
      "Life_000": {
        "score": 10.95,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_000_20260602_031351",
        "cost_usd": 3.06,
        "duration_seconds": 918
      },
      "Life_001": {
        "score": 15.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_001_20260602_033122",
        "cost_usd": 1.556667,
        "duration_seconds": 467
      },
      "Life_002": {
        "score": 2.1,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_002_20260602_034308",
        "cost_usd": 1.61,
        "duration_seconds": 483
      },
      "Life_003": {
        "score": 24.1,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Life_003_20260602_035327",
        "cost_usd": 1.42,
        "duration_seconds": 426
      },
      "Material_000": {
        "score": 26,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_000_20260602_040045",
        "cost_usd": 3.736667,
        "duration_seconds": 1121
      },
      "Material_001": {
        "score": 14.7,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_001_20260602_041939",
        "cost_usd": 1.653333,
        "duration_seconds": 496
      },
      "Material_002": {
        "score": 39.42,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_002_20260602_042808",
        "cost_usd": 6.963333,
        "duration_seconds": 2089
      },
      "Material_003": {
        "score": 18.6,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Material_003_20260602_050310",
        "cost_usd": 3.386667,
        "duration_seconds": 1016
      },
      "Math_000": {
        "score": 35.9,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_000_20260602_052038",
        "cost_usd": 1.866667,
        "duration_seconds": 560
      },
      "Math_001": {
        "score": 14.3,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_001_20260602_053007",
        "cost_usd": 1.83,
        "duration_seconds": 549
      },
      "Math_002": {
        "score": 5.5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_002_20260602_054317",
        "cost_usd": 21.413333,
        "duration_seconds": 6424
      },
      "Math_003": {
        "score": 10,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Math_003_20260602_073157",
        "cost_usd": 8.756667,
        "duration_seconds": 2627
      },
      "Neuroscience_000": {
        "score": 5,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_000_20260602_081550",
        "cost_usd": 2.403333,
        "duration_seconds": 721
      },
      "Neuroscience_001": {
        "score": 5.75,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_001_20260602_083001",
        "cost_usd": 7.63,
        "duration_seconds": 2289
      },
      "Neuroscience_002": {
        "score": 1.25,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_002_20260602_091210",
        "cost_usd": 4.34,
        "duration_seconds": 1302
      },
      "Neuroscience_003": {
        "score": 5.85,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Neuroscience_003_20260602_093753",
        "cost_usd": 3.156667,
        "duration_seconds": 947
      },
      "Physics_000": {
        "score": 37.2,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_000_20260602_095453",
        "cost_usd": 6.76,
        "duration_seconds": 2028
      },
      "Physics_001": {
        "score": 32.3,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_001_20260602_102928",
        "cost_usd": 2.36,
        "duration_seconds": 708
      },
      "Physics_002": {
        "score": 37.65,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_002_20260602_104126",
        "cost_usd": 1.44,
        "duration_seconds": 432
      },
      "Physics_003": {
        "score": 48.6,
        "model": "claude-opus-4-8",
        "model_display": "Claude-Opus-4.8",
        "run_id": "Physics_003_20260602_104851",
        "cost_usd": 2.13,
        "duration_seconds": 639
      }
    },
    "ResearchHarness (DeepSeek-V4-Pro)": {
      "Astronomy_000": {
        "score": 25.6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Astronomy_000_20260515_153403",
        "cost_usd": 0.185781,
        "duration_seconds": 1025
      },
      "Astronomy_001": {
        "score": 6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Astronomy_001_20260515_155108",
        "cost_usd": 0.093344,
        "duration_seconds": 515
      },
      "Astronomy_002": {
        "score": 22.1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Astronomy_002_20260515_155943",
        "cost_usd": 0.21025,
        "duration_seconds": 1160
      },
      "Astronomy_003": {
        "score": 47.1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Astronomy_003_20260515_161903",
        "cost_usd": 0.125606,
        "duration_seconds": 693
      },
      "Chemistry_000": {
        "score": 15.1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Chemistry_000_20260518_001006",
        "cost_usd": 1.214375,
        "duration_seconds": 6700
      },
      "Chemistry_001": {
        "score": 5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Chemistry_001_20260515_190038",
        "cost_usd": 0.185237,
        "duration_seconds": 1022
      },
      "Chemistry_002": {
        "score": 0,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Chemistry_002_20260515_191740",
        "cost_usd": 0.125244,
        "duration_seconds": 691
      },
      "Chemistry_003": {
        "score": 10,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Chemistry_003_20260515_192911",
        "cost_usd": 0.523087,
        "duration_seconds": 2886
      },
      "Earth_000": {
        "score": 16.7,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Earth_000_20260515_201717",
        "cost_usd": 0.480856,
        "duration_seconds": 2653
      },
      "Earth_001": {
        "score": 37.38,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Earth_001_20260515_210130",
        "cost_usd": 0.105306,
        "duration_seconds": 581
      },
      "Earth_002": {
        "score": 25.5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Earth_002_20260515_211111",
        "cost_usd": 0.211156,
        "duration_seconds": 1165
      },
      "Earth_003": {
        "score": 1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Earth_003_20260515_213036",
        "cost_usd": 0.186869,
        "duration_seconds": 1031
      },
      "Energy_000": {
        "score": 17.5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Energy_000_20260515_214747",
        "cost_usd": 0.274775,
        "duration_seconds": 1516
      },
      "Energy_001": {
        "score": 25,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Energy_001_20260515_221303",
        "cost_usd": 0.253206,
        "duration_seconds": 1397
      },
      "Energy_002": {
        "score": 38.65,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Energy_002_20260515_223620",
        "cost_usd": 0.180706,
        "duration_seconds": 997
      },
      "Energy_003": {
        "score": 6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Energy_003_20260515_225258",
        "cost_usd": 0.160769,
        "duration_seconds": 887
      },
      "Information_000": {
        "score": 0,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Information_000_20260515_230745",
        "cost_usd": 0.179075,
        "duration_seconds": 988
      },
      "Information_001": {
        "score": 1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Information_001_20260515_232413",
        "cost_usd": 0.131406,
        "duration_seconds": 725
      },
      "Information_002": {
        "score": 12.9,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Information_002_20260515_233618",
        "cost_usd": 0.139381,
        "duration_seconds": 769
      },
      "Information_003": {
        "score": 4.6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Information_003_20260515_234907",
        "cost_usd": 0.52635,
        "duration_seconds": 2904
      },
      "Life_000": {
        "score": 10.15,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Life_000_20260516_003731",
        "cost_usd": 0.277856,
        "duration_seconds": 1533
      },
      "Life_001": {
        "score": 9.5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Life_001_20260516_010304",
        "cost_usd": 0.117087,
        "duration_seconds": 646
      },
      "Life_002": {
        "score": 1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Life_002_20260516_011350",
        "cost_usd": 0.259369,
        "duration_seconds": 1431
      },
      "Life_003": {
        "score": 32.5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Life_003_20260516_013741",
        "cost_usd": 0.173638,
        "duration_seconds": 958
      },
      "Material_000": {
        "score": 24,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Material_000_20260516_015340",
        "cost_usd": 0.9744,
        "duration_seconds": 5376
      },
      "Material_001": {
        "score": 21,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Material_001_20260516_032315",
        "cost_usd": 0.142281,
        "duration_seconds": 785
      },
      "Material_002": {
        "score": 38.4,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Material_002_20260516_033621",
        "cost_usd": 0.348362,
        "duration_seconds": 1922
      },
      "Material_003": {
        "score": 15.15,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Material_003_20260516_040823",
        "cost_usd": 0.366125,
        "duration_seconds": 2020
      },
      "Math_000": {
        "score": 23.35,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Math_000_20260516_044203",
        "cost_usd": 0.537406,
        "duration_seconds": 2965
      },
      "Math_001": {
        "score": 22.9,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Math_001_20260516_053128",
        "cost_usd": 0.125244,
        "duration_seconds": 691
      },
      "Math_002": {
        "score": 7.5,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Math_002_20260516_054259",
        "cost_usd": 0.448775,
        "duration_seconds": 2476
      },
      "Neuroscience_000": {
        "score": 10,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Neuroscience_000_20260516_062458",
        "cost_usd": 0.179437,
        "duration_seconds": 990
      },
      "Neuroscience_001": {
        "score": 7.05,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Neuroscience_001_20260516_064127",
        "cost_usd": 0.136662,
        "duration_seconds": 754
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Neuroscience_002_20260516_065402",
        "cost_usd": 0.265531,
        "duration_seconds": 1465
      },
      "Neuroscience_003": {
        "score": 13.65,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Neuroscience_003_20260516_071828",
        "cost_usd": 0.138475,
        "duration_seconds": 764
      },
      "Physics_000": {
        "score": 14.1,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Physics_000_20260516_073111",
        "cost_usd": 0.166931,
        "duration_seconds": 921
      },
      "Physics_001": {
        "score": 38.6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Physics_001_20260516_074632",
        "cost_usd": 0.313925,
        "duration_seconds": 1732
      },
      "Physics_002": {
        "score": 28.2,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Physics_002_20260516_081523",
        "cost_usd": 0.144456,
        "duration_seconds": 797
      },
      "Physics_003": {
        "score": 33.6,
        "model": "DeepSeek-V4-Pro",
        "model_display": "DeepSeek-V4-Pro",
        "run_id": "Physics_003_20260516_082845",
        "cost_usd": 0.228012,
        "duration_seconds": 1258
      }
    },
    "ResearchHarness (GLM-5.1)": {
      "Astronomy_000": {
        "score": 9,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Astronomy_000_20260414_195806",
        "cost_usd": 1.345183,
        "duration_seconds": 1877
      },
      "Astronomy_001": {
        "score": 37,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Astronomy_001_20260414_202922",
        "cost_usd": 1.267783,
        "duration_seconds": 1769
      },
      "Astronomy_002": {
        "score": 29.9,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Astronomy_002_20260414_205851",
        "cost_usd": 1.76085,
        "duration_seconds": 2457
      },
      "Astronomy_003": {
        "score": 43.1,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Astronomy_003_20260414_213949",
        "cost_usd": 0.3182,
        "duration_seconds": 444
      },
      "Chemistry_000": {
        "score": 18.95,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Chemistry_000_20260416_104049",
        "cost_usd": 3.9904,
        "duration_seconds": 5568
      },
      "Chemistry_001": {
        "score": 2.75,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Chemistry_001_20260415_001714",
        "cost_usd": 1.42115,
        "duration_seconds": 1983
      },
      "Chemistry_002": {
        "score": 1.4,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Chemistry_002_20260415_005017",
        "cost_usd": 0.558283,
        "duration_seconds": 779
      },
      "Chemistry_003": {
        "score": 22.5,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Chemistry_003_20260415_010316",
        "cost_usd": 2.316983,
        "duration_seconds": 3233
      },
      "Earth_000": {
        "score": 14.8,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Earth_000_20260415_015710",
        "cost_usd": 0.489483,
        "duration_seconds": 683
      },
      "Earth_001": {
        "score": 33.04,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Earth_001_20260415_020834",
        "cost_usd": 0.40635,
        "duration_seconds": 567
      },
      "Earth_002": {
        "score": 30.4,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Earth_002_20260415_021801",
        "cost_usd": 0.714517,
        "duration_seconds": 997
      },
      "Earth_003": {
        "score": 4,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Earth_003_20260415_023438",
        "cost_usd": 1.2384,
        "duration_seconds": 1728
      },
      "Energy_000": {
        "score": 16,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Energy_000_20260415_030326",
        "cost_usd": 1.745083,
        "duration_seconds": 2435
      },
      "Energy_001": {
        "score": 18.2,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Energy_001_20260415_034401",
        "cost_usd": 0.6923,
        "duration_seconds": 966
      },
      "Energy_002": {
        "score": 39.85,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Energy_002_20260415_040007",
        "cost_usd": 0.515283,
        "duration_seconds": 719
      },
      "Energy_003": {
        "score": 7.5,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Energy_003_20260415_041206",
        "cost_usd": 0.620633,
        "duration_seconds": 866
      },
      "Information_000": {
        "score": 19.5,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Information_000_20260415_211636",
        "cost_usd": 1.0234,
        "duration_seconds": 1428
      },
      "Information_001": {
        "score": 0.6,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Information_001_20260415_214024",
        "cost_usd": 0.444333,
        "duration_seconds": 620
      },
      "Information_002": {
        "score": 36.2,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Information_002_20260415_215045",
        "cost_usd": 0.439317,
        "duration_seconds": 613
      },
      "Information_003": {
        "score": 8.65,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Information_003_20260415_220058",
        "cost_usd": 1.2255,
        "duration_seconds": 1710
      },
      "Life_000": {
        "score": 9.95,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Life_000_20260415_094513",
        "cost_usd": 1.2814,
        "duration_seconds": 1788
      },
      "Life_001": {
        "score": 8.75,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Life_001_20260415_101501",
        "cost_usd": 0.558283,
        "duration_seconds": 779
      },
      "Life_002": {
        "score": 6.3,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Life_002_20260415_102800",
        "cost_usd": 0.85785,
        "duration_seconds": 1197
      },
      "Life_003": {
        "score": 23.8,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Life_003_20260415_110858",
        "cost_usd": 1.060667,
        "duration_seconds": 1480
      },
      "Material_000": {
        "score": 21.7,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Material_000_20260415_113339",
        "cost_usd": 4.399617,
        "duration_seconds": 6139
      },
      "Material_001": {
        "score": 4.15,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Material_001_20260415_131558",
        "cost_usd": 1.084317,
        "duration_seconds": 1513
      },
      "Material_002": {
        "score": 28.4,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Material_002_20260415_134111",
        "cost_usd": 1.61035,
        "duration_seconds": 2247
      },
      "Material_003": {
        "score": 20.3,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Material_003_20260415_141838",
        "cost_usd": 3.905833,
        "duration_seconds": 5450
      },
      "Math_000": {
        "score": 23.95,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Math_000_20260415_094450",
        "cost_usd": 1.7587,
        "duration_seconds": 2454
      },
      "Math_001": {
        "score": 27,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Math_001_20260415_160410",
        "cost_usd": 2.460317,
        "duration_seconds": 3433
      },
      "Math_002": {
        "score": 10.9,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Math_002_20260416_105258",
        "cost_usd": 2.07045,
        "duration_seconds": 2889
      },
      "Math_003": {
        "score": 10,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Math_003_20260415_180131",
        "cost_usd": 1.08575,
        "duration_seconds": 1515
      },
      "Neuroscience_000": {
        "score": 10.4,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Neuroscience_000_20260415_182645",
        "cost_usd": 0.702333,
        "duration_seconds": 980
      },
      "Neuroscience_001": {
        "score": 2.55,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Neuroscience_001_20260415_184305",
        "cost_usd": 0.771133,
        "duration_seconds": 1076
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Neuroscience_002_20260415_190101",
        "cost_usd": 0.9933,
        "duration_seconds": 1386
      },
      "Neuroscience_003": {
        "score": 9.45,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Neuroscience_003_20260415_192407",
        "cost_usd": 1.448383,
        "duration_seconds": 2021
      },
      "Physics_000": {
        "score": 23.8,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Physics_000_20260415_195749",
        "cost_usd": 0.713083,
        "duration_seconds": 995
      },
      "Physics_001": {
        "score": 31.9,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Physics_001_20260415_201423",
        "cost_usd": 0.964633,
        "duration_seconds": 1346
      },
      "Physics_002": {
        "score": 32.9,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Physics_002_20260415_203649",
        "cost_usd": 0.985417,
        "duration_seconds": 1375
      },
      "Physics_003": {
        "score": 27.1,
        "model": "GLM-5.1",
        "model_display": "GLM-5.1",
        "run_id": "Physics_003_20260415_205947",
        "cost_usd": 0.723117,
        "duration_seconds": 1009
      }
    },
    "ResearchHarness (GLM-5.2)": {
      "Astronomy_000": {
        "score": 33.1,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Astronomy_000_20260622_141153",
        "cost_usd": 0.983775,
        "duration_seconds": 2018
      },
      "Astronomy_001": {
        "score": 39.2,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Astronomy_001_20260622_144544",
        "cost_usd": 0.96525,
        "duration_seconds": 1980
      },
      "Astronomy_002": {
        "score": 25,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Astronomy_002_20260622_151902",
        "cost_usd": 1.52685,
        "duration_seconds": 3132
      },
      "Astronomy_003": {
        "score": 48,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Astronomy_003_20260622_161132",
        "cost_usd": 0.433875,
        "duration_seconds": 890
      },
      "Chemistry_000": {
        "score": 21.55,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Chemistry_000_20260622_164749",
        "cost_usd": 2.108925,
        "duration_seconds": 4326
      },
      "Chemistry_001": {
        "score": 1.5,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Chemistry_001_20260622_180009",
        "cost_usd": 1.42935,
        "duration_seconds": 2932
      },
      "Chemistry_002": {
        "score": 0,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Chemistry_002_20260622_185040",
        "cost_usd": 1.392787,
        "duration_seconds": 2857
      },
      "Chemistry_003": {
        "score": 13.5,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Chemistry_003_20260622_193831",
        "cost_usd": 1.671637,
        "duration_seconds": 3429
      },
      "Earth_000": {
        "score": 12.7,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Earth_000_20260622_203555",
        "cost_usd": 0.5811,
        "duration_seconds": 1192
      },
      "Earth_001": {
        "score": 37.29,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Earth_001_20260622_205609",
        "cost_usd": 0.712237,
        "duration_seconds": 1461
      },
      "Earth_002": {
        "score": 16.8,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Earth_002_20260622_212052",
        "cost_usd": 0.67665,
        "duration_seconds": 1388
      },
      "Earth_003": {
        "score": 9.6,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Earth_003_20260622_214424",
        "cost_usd": 0.798037,
        "duration_seconds": 1637
      },
      "Energy_000": {
        "score": 22,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Energy_000_20260622_221209",
        "cost_usd": 2.534025,
        "duration_seconds": 5198
      },
      "Energy_001": {
        "score": 16.7,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Energy_001_20260622_233902",
        "cost_usd": 0.747337,
        "duration_seconds": 1533
      },
      "Energy_002": {
        "score": 38.55,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Energy_002_20260623_000450",
        "cost_usd": 0.490913,
        "duration_seconds": 1007
      },
      "Energy_003": {
        "score": 16,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Energy_003_20260623_002152",
        "cost_usd": 0.88335,
        "duration_seconds": 1812
      },
      "Information_000": {
        "score": 3.2,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Information_000_20260623_005220",
        "cost_usd": 1.1037,
        "duration_seconds": 2264
      },
      "Information_001": {
        "score": 0.6,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Information_001_20260623_013015",
        "cost_usd": 1.56585,
        "duration_seconds": 3212
      },
      "Information_002": {
        "score": 39.3,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Information_002_20260623_022404",
        "cost_usd": 0.502613,
        "duration_seconds": 1031
      },
      "Information_003": {
        "score": 1.35,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Information_003_20260623_024121",
        "cost_usd": 1.291387,
        "duration_seconds": 2649
      },
      "Life_000": {
        "score": 7.8,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Life_000_20260623_032545",
        "cost_usd": 0.8424,
        "duration_seconds": 1728
      },
      "Life_001": {
        "score": 19.4,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Life_001_20260623_035449",
        "cost_usd": 0.467025,
        "duration_seconds": 958
      },
      "Life_002": {
        "score": 6.1,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Life_002_20260623_041102",
        "cost_usd": 0.625462,
        "duration_seconds": 1283
      },
      "Life_003": {
        "score": 37.3,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Life_003_20260623_043233",
        "cost_usd": 0.507975,
        "duration_seconds": 1042
      },
      "Material_000": {
        "score": 17,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Material_000_20260623_045007",
        "cost_usd": 1.894912,
        "duration_seconds": 3887
      },
      "Material_001": {
        "score": 19,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Material_001_20260623_055505",
        "cost_usd": 0.401212,
        "duration_seconds": 823
      },
      "Material_002": {
        "score": 29.52,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Material_002_20260623_060901",
        "cost_usd": 2.086987,
        "duration_seconds": 4281
      },
      "Material_003": {
        "score": 23.85,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Material_003_20260623_072052",
        "cost_usd": 2.131838,
        "duration_seconds": 4373
      },
      "Math_000": {
        "score": 27.4,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Math_000_20260623_083358",
        "cost_usd": 1.315762,
        "duration_seconds": 2699
      },
      "Math_001": {
        "score": 39.1,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Math_001_20260623_091909",
        "cost_usd": 1.065187,
        "duration_seconds": 2185
      },
      "Math_002": {
        "score": 13.2,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Math_002_20260623_095546",
        "cost_usd": 2.0397,
        "duration_seconds": 4184
      },
      "Math_003": {
        "score": 26,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Math_003_20260623_110544",
        "cost_usd": 3.024938,
        "duration_seconds": 6205
      },
      "Neuroscience_000": {
        "score": 6,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Neuroscience_000_20260623_124913",
        "cost_usd": 0.4953,
        "duration_seconds": 1016
      },
      "Neuroscience_001": {
        "score": 14.5,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Neuroscience_001_20260623_130626",
        "cost_usd": 2.688563,
        "duration_seconds": 5515
      },
      "Neuroscience_002": {
        "score": 0.5,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Neuroscience_002_20260623_143841",
        "cost_usd": 2.2074,
        "duration_seconds": 4528
      },
      "Neuroscience_003": {
        "score": 17.6,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Neuroscience_003_20260623_155429",
        "cost_usd": 0.892612,
        "duration_seconds": 1831
      },
      "Physics_000": {
        "score": 36.6,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Physics_000_20260623_162517",
        "cost_usd": 1.735013,
        "duration_seconds": 3559
      },
      "Physics_001": {
        "score": 33.95,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Physics_001_20260623_172451",
        "cost_usd": 0.98865,
        "duration_seconds": 2028
      },
      "Physics_003": {
        "score": 36.9,
        "model": "GLM-5.2",
        "model_display": "GLM-5.2",
        "run_id": "Physics_003_20260623_210122",
        "cost_usd": 0.476775,
        "duration_seconds": 978
      }
    },
    "ResearchHarness (GPT-5.4)": {
      "Astronomy_000": {
        "score": 24.9,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_000_20260414_113238",
        "cost_usd": 2.20125,
        "duration_seconds": 1174
      },
      "Astronomy_001": {
        "score": 4,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_001_20260414_170852",
        "cost_usd": 0.665625,
        "duration_seconds": 355
      },
      "Astronomy_002": {
        "score": 14.6,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_002_20260414_170852",
        "cost_usd": 0.913125,
        "duration_seconds": 487
      },
      "Astronomy_003": {
        "score": 44.8,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Astronomy_003_20260414_170852",
        "cost_usd": 0.69,
        "duration_seconds": 368
      },
      "Chemistry_000": {
        "score": 17.05,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_000_20260414_195840",
        "cost_usd": 5.431875,
        "duration_seconds": 2897
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_001_20260414_170852",
        "cost_usd": 0.70875,
        "duration_seconds": 378
      },
      "Chemistry_002": {
        "score": 1,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_002_20260414_170852",
        "cost_usd": 0.7725,
        "duration_seconds": 412
      },
      "Chemistry_003": {
        "score": 9,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Chemistry_003_20260414_170852",
        "cost_usd": 0.905625,
        "duration_seconds": 483
      },
      "Earth_000": {
        "score": 12.1,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_000_20260414_170852",
        "cost_usd": 0.811875,
        "duration_seconds": 433
      },
      "Earth_001": {
        "score": 36.71,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_001_20260414_171447",
        "cost_usd": 0.691875,
        "duration_seconds": 369
      },
      "Earth_002": {
        "score": 25,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_002_20260414_171501",
        "cost_usd": 0.976875,
        "duration_seconds": 521
      },
      "Earth_003": {
        "score": 1.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Earth_003_20260414_171511",
        "cost_usd": 0.883125,
        "duration_seconds": 471
      },
      "Energy_000": {
        "score": 11.8,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_000_20260414_195840",
        "cost_usd": 1.951875,
        "duration_seconds": 1041
      },
      "Energy_001": {
        "score": 8.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_001_20260414_201619",
        "cost_usd": 1.198125,
        "duration_seconds": 639
      },
      "Energy_002": {
        "score": 28.75,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_002_20260414_171655",
        "cost_usd": 1.314375,
        "duration_seconds": 701
      },
      "Energy_003": {
        "score": 19.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Energy_003_20260414_171659",
        "cost_usd": 0.765,
        "duration_seconds": 408
      },
      "Information_000": {
        "score": 29,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_000_20260414_172057",
        "cost_usd": 0.706875,
        "duration_seconds": 377
      },
      "Information_001": {
        "score": 0,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_001_20260414_202717",
        "cost_usd": 1.254375,
        "duration_seconds": 669
      },
      "Information_002": {
        "score": 22.9,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_002_20260414_203902",
        "cost_usd": 1.23,
        "duration_seconds": 656
      },
      "Information_003": {
        "score": 11,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Information_003_20260414_204710",
        "cost_usd": 2.086875,
        "duration_seconds": 1113
      },
      "Life_000": {
        "score": 8.85,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_000_20260414_205006",
        "cost_usd": 1.84875,
        "duration_seconds": 986
      },
      "Life_001": {
        "score": 7.45,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_001_20260414_210600",
        "cost_usd": 1.456875,
        "duration_seconds": 777
      },
      "Life_002": {
        "score": 8.8,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_002_20260414_210650",
        "cost_usd": 1.494375,
        "duration_seconds": 797
      },
      "Life_003": {
        "score": 31.8,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Life_003_20260414_211912",
        "cost_usd": 1.52625,
        "duration_seconds": 814
      },
      "Material_000": {
        "score": 5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_000_20260414_212015",
        "cost_usd": 2.034375,
        "duration_seconds": 1085
      },
      "Material_001": {
        "score": 3.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_001_20260414_213300",
        "cost_usd": 1.426875,
        "duration_seconds": 761
      },
      "Material_002": {
        "score": 3.3,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_002_20260414_213833",
        "cost_usd": 1.059375,
        "duration_seconds": 565
      },
      "Material_003": {
        "score": 18.8,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Material_003_20260414_214555",
        "cost_usd": 2.150625,
        "duration_seconds": 1147
      },
      "Math_000": {
        "score": 11,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_000_20260414_214810",
        "cost_usd": 1.591875,
        "duration_seconds": 849
      },
      "Math_001": {
        "score": 42,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_001_20260414_220232",
        "cost_usd": 1.040625,
        "duration_seconds": 555
      },
      "Math_002": {
        "score": 10.2,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_002_20260414_220537",
        "cost_usd": 1.209375,
        "duration_seconds": 645
      },
      "Math_003": {
        "score": 10,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Math_003_20260414_221200",
        "cost_usd": 1.314375,
        "duration_seconds": 701
      },
      "Neuroscience_000": {
        "score": 13,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_000_20260414_221650",
        "cost_usd": 4.27125,
        "duration_seconds": 2278
      },
      "Neuroscience_001": {
        "score": 2.2,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_001_20260414_222526",
        "cost_usd": 2.814375,
        "duration_seconds": 1501
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_002_20260414_225053",
        "cost_usd": 14.19375,
        "duration_seconds": 7570
      },
      "Neuroscience_003": {
        "score": 4.35,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Neuroscience_003_20260414_225711",
        "cost_usd": 13.438125,
        "duration_seconds": 7167
      },
      "Physics_000": {
        "score": 19.2,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_000_20260415_005716",
        "cost_usd": 1.36125,
        "duration_seconds": 726
      },
      "Physics_001": {
        "score": 28.5,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_001_20260415_005728",
        "cost_usd": 2.0025,
        "duration_seconds": 1068
      },
      "Physics_002": {
        "score": 18.4,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_002_20260415_010948",
        "cost_usd": 1.1775,
        "duration_seconds": 628
      },
      "Physics_003": {
        "score": 42.1,
        "model": "GPT-5.4",
        "model_display": "GPT-5.4",
        "run_id": "Physics_003_20260415_011540",
        "cost_usd": 1.408125,
        "duration_seconds": 751
      }
    },
    "ResearchHarness (GPT-5.5)": {
      "Astronomy_000": {
        "score": 26,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_000_20260429_160234",
        "cost_usd": 1.785,
        "duration_seconds": 476
      },
      "Astronomy_001": {
        "score": 2,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_001_20260429_160234",
        "cost_usd": 1.24125,
        "duration_seconds": 331
      },
      "Astronomy_002": {
        "score": 24.5,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_002_20260429_160819",
        "cost_usd": 1.395,
        "duration_seconds": 372
      },
      "Astronomy_003": {
        "score": 43.4,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Astronomy_003_20260429_161044",
        "cost_usd": 1.035,
        "duration_seconds": 276
      },
      "Chemistry_000": {
        "score": 19.1,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_000_20260429_161444",
        "cost_usd": 2.29875,
        "duration_seconds": 613
      },
      "Chemistry_001": {
        "score": 2,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_001_20260429_161544",
        "cost_usd": 1.41375,
        "duration_seconds": 377
      },
      "Chemistry_002": {
        "score": 5,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_002_20260429_162220",
        "cost_usd": 0.9675,
        "duration_seconds": 258
      },
      "Chemistry_003": {
        "score": 15.5,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Chemistry_003_20260429_162510",
        "cost_usd": 1.83375,
        "duration_seconds": 489
      },
      "Earth_000": {
        "score": 21.8,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_000_20260429_162650",
        "cost_usd": 1.0275,
        "duration_seconds": 274
      },
      "Earth_001": {
        "score": 39.24,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_001_20260429_163146",
        "cost_usd": 0.68625,
        "duration_seconds": 183
      },
      "Earth_002": {
        "score": 11.8,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_002_20260429_163331",
        "cost_usd": 1.27875,
        "duration_seconds": 341
      },
      "Earth_003": {
        "score": 0.6,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Earth_003_20260429_163506",
        "cost_usd": 0.91125,
        "duration_seconds": 243
      },
      "Energy_000": {
        "score": 16,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_000_20260429_163926",
        "cost_usd": 1.89375,
        "duration_seconds": 505
      },
      "Energy_001": {
        "score": 20.1,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_001_20260429_163931",
        "cost_usd": 7.7175,
        "duration_seconds": 2058
      },
      "Energy_002": {
        "score": 37,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_002_20260429_164806",
        "cost_usd": 0.9975,
        "duration_seconds": 266
      },
      "Energy_003": {
        "score": 17.5,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Energy_003_20260429_165242",
        "cost_usd": 0.79875,
        "duration_seconds": 213
      },
      "Information_000": {
        "score": 22.7,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_000_20260429_165637",
        "cost_usd": 0.88125,
        "duration_seconds": 235
      },
      "Information_001": {
        "score": 6,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_001_20260429_170047",
        "cost_usd": 1.09875,
        "duration_seconds": 293
      },
      "Information_002": {
        "score": 33.1,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_002_20260429_170607",
        "cost_usd": 1.04625,
        "duration_seconds": 279
      },
      "Information_003": {
        "score": 9.55,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Information_003_20260429_171107",
        "cost_usd": 7.79625,
        "duration_seconds": 2079
      },
      "Life_000": {
        "score": 2.25,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_000_20260429_171403",
        "cost_usd": 5.05875,
        "duration_seconds": 1349
      },
      "Life_001": {
        "score": 7.2,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_001_20260429_173722",
        "cost_usd": 1.0725,
        "duration_seconds": 286
      },
      "Life_002": {
        "score": 8.5,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_002_20260429_174238",
        "cost_usd": 1.64625,
        "duration_seconds": 439
      },
      "Life_003": {
        "score": 29.4,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Life_003_20260429_174558",
        "cost_usd": 0.9225,
        "duration_seconds": 246
      },
      "Material_000": {
        "score": 5.6,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_000_20260429_175003",
        "cost_usd": 5.54625,
        "duration_seconds": 1479
      },
      "Material_001": {
        "score": 8,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_001_20260429_175018",
        "cost_usd": 0.84,
        "duration_seconds": 224
      },
      "Material_002": {
        "score": 26.09,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_002_20260429_175413",
        "cost_usd": 1.09125,
        "duration_seconds": 291
      },
      "Material_003": {
        "score": 18.95,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Material_003_20260429_175919",
        "cost_usd": 2.8125,
        "duration_seconds": 750
      },
      "Math_000": {
        "score": 8.25,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_000_20260429_181207",
        "cost_usd": 0.91125,
        "duration_seconds": 243
      },
      "Math_001": {
        "score": 23,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_001_20260429_181452",
        "cost_usd": 1.9125,
        "duration_seconds": 510
      },
      "Math_002": {
        "score": 11,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_002_20260429_181622",
        "cost_usd": 1.87875,
        "duration_seconds": 501
      },
      "Math_003": {
        "score": 10,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Math_003_20260429_182334",
        "cost_usd": 1.1625,
        "duration_seconds": 310
      },
      "Neuroscience_000": {
        "score": 11,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_000_20260429_182509",
        "cost_usd": 0.8925,
        "duration_seconds": 238
      },
      "Neuroscience_001": {
        "score": 3.75,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_001_20260429_182849",
        "cost_usd": 1.93875,
        "duration_seconds": 517
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_002_20260429_182919",
        "cost_usd": 0.80625,
        "duration_seconds": 215
      },
      "Neuroscience_003": {
        "score": 9.6,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Neuroscience_003_20260429_183309",
        "cost_usd": 2.62875,
        "duration_seconds": 701
      },
      "Physics_000": {
        "score": 18.3,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_000_20260429_183745",
        "cost_usd": 0.7575,
        "duration_seconds": 202
      },
      "Physics_001": {
        "score": 29.75,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_001_20260429_184120",
        "cost_usd": 0.9975,
        "duration_seconds": 266
      },
      "Physics_002": {
        "score": 26.4,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_002_20260429_184505",
        "cost_usd": 0.89625,
        "duration_seconds": 239
      },
      "Physics_003": {
        "score": 49,
        "model": "GPT-5.5",
        "model_display": "GPT-5.5",
        "run_id": "Physics_003_20260429_184601",
        "cost_usd": 0.99,
        "duration_seconds": 264
      }
    },
    "ResearchHarness (Gemini-3.1-Pro)": {
      "Astronomy_000": {
        "score": 7.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Astronomy_000_20260415_162619",
        "cost_usd": 3.102,
        "duration_seconds": 2068
      },
      "Astronomy_001": {
        "score": 4,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Astronomy_001_20260415_162323",
        "cost_usd": 0.213,
        "duration_seconds": 142
      },
      "Astronomy_002": {
        "score": 20,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Astronomy_002_20260416_132754",
        "cost_usd": 1.371,
        "duration_seconds": 914
      },
      "Astronomy_003": {
        "score": 45.8,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Astronomy_003_20260415_170228",
        "cost_usd": 0.2445,
        "duration_seconds": 163
      },
      "Chemistry_000": {
        "score": 19.6,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Chemistry_000_20260416_180812",
        "cost_usd": 4.3785,
        "duration_seconds": 2919
      },
      "Chemistry_001": {
        "score": 4.25,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Chemistry_001_20260415_190626",
        "cost_usd": 0.8025,
        "duration_seconds": 535
      },
      "Chemistry_002": {
        "score": 0,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Chemistry_002_20260415_193549",
        "cost_usd": 0.264,
        "duration_seconds": 176
      },
      "Earth_000": {
        "score": 14.8,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Earth_000_20260415_200139",
        "cost_usd": 0.294,
        "duration_seconds": 196
      },
      "Earth_001": {
        "score": 28.05,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Earth_001_20260415_200511",
        "cost_usd": 0.366,
        "duration_seconds": 244
      },
      "Earth_002": {
        "score": 11,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Earth_002_20260415_200932",
        "cost_usd": 0.45,
        "duration_seconds": 300
      },
      "Earth_003": {
        "score": 1.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Earth_003_20260415_201446",
        "cost_usd": 0.8625,
        "duration_seconds": 575
      },
      "Energy_000": {
        "score": 3.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Energy_000_20260416_135241",
        "cost_usd": 0.7935,
        "duration_seconds": 529
      },
      "Energy_001": {
        "score": 3,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Energy_001_20260415_232419",
        "cost_usd": 1.4055,
        "duration_seconds": 937
      },
      "Energy_002": {
        "score": 21.25,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Energy_002_20260415_234011",
        "cost_usd": 0.624,
        "duration_seconds": 416
      },
      "Energy_003": {
        "score": 20.3,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Energy_003_20260415_234723",
        "cost_usd": 0.216,
        "duration_seconds": 144
      },
      "Information_000": {
        "score": 10.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Information_000_20260415_234958",
        "cost_usd": 0.909,
        "duration_seconds": 606
      },
      "Information_001": {
        "score": 1,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Information_001_20260416_135421",
        "cost_usd": 1.5345,
        "duration_seconds": 1023
      },
      "Information_002": {
        "score": 8.8,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Information_002_20260416_010053",
        "cost_usd": 0.642,
        "duration_seconds": 428
      },
      "Life_000": {
        "score": 3.55,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Life_000_20260416_104333",
        "cost_usd": 0.4155,
        "duration_seconds": 277
      },
      "Life_001": {
        "score": 8.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Life_001_20260416_104333",
        "cost_usd": 0.2805,
        "duration_seconds": 187
      },
      "Life_002": {
        "score": 7.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Life_002_20260416_141143",
        "cost_usd": 6.2025,
        "duration_seconds": 4135
      },
      "Life_003": {
        "score": 18,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Life_003_20260416_104825",
        "cost_usd": 0.159,
        "duration_seconds": 106
      },
      "Material_000": {
        "score": 20,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Material_000_20260416_141659",
        "cost_usd": 11.1495,
        "duration_seconds": 7433
      },
      "Material_001": {
        "score": 5.25,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Material_001_20260416_111314",
        "cost_usd": 0.408,
        "duration_seconds": 272
      },
      "Material_003": {
        "score": 8.7,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Material_003_20260416_114219",
        "cost_usd": 4.4415,
        "duration_seconds": 2961
      },
      "Math_000": {
        "score": 21.1,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Math_000_20260416_114950",
        "cost_usd": 2.691,
        "duration_seconds": 1794
      },
      "Math_001": {
        "score": 13.5,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Math_001_20260416_121957",
        "cost_usd": 1.443,
        "duration_seconds": 962
      },
      "Math_003": {
        "score": 10.35,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Math_003_20260416_162104",
        "cost_usd": 0.297,
        "duration_seconds": 198
      },
      "Neuroscience_000": {
        "score": 2,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Neuroscience_000_20260416_123952",
        "cost_usd": 0.1455,
        "duration_seconds": 97
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Neuroscience_002_20260416_130633",
        "cost_usd": 0.294,
        "duration_seconds": 196
      },
      "Neuroscience_003": {
        "score": 2.7,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Neuroscience_003_20260416_131003",
        "cost_usd": 0.5145,
        "duration_seconds": 343
      },
      "Physics_000": {
        "score": 22,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Physics_000_20260416_162550",
        "cost_usd": 2.9655,
        "duration_seconds": 1977
      },
      "Physics_001": {
        "score": 22.55,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Physics_001_20260416_131118",
        "cost_usd": 0.144,
        "duration_seconds": 96
      },
      "Physics_002": {
        "score": 27.55,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Physics_002_20260416_165907",
        "cost_usd": 5.475,
        "duration_seconds": 3650
      },
      "Physics_003": {
        "score": 46.8,
        "model": "Gemini-3.1-Pro",
        "model_display": "Gemini-3.1-Pro",
        "run_id": "Physics_003_20260416_131439",
        "cost_usd": 0.4995,
        "duration_seconds": 333
      }
    },
    "ResearchHarness (Gemini-3.5-Flash)": {
      "Astronomy_000": {
        "score": 24,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Astronomy_000_20260527_101521",
        "cost_usd": 0.9135,
        "duration_seconds": 812
      },
      "Astronomy_001": {
        "score": 13.2,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Astronomy_001_20260527_165228",
        "cost_usd": 3.760875,
        "duration_seconds": 3343
      },
      "Astronomy_003": {
        "score": 47,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Astronomy_003_20260526_204227",
        "cost_usd": 0.646875,
        "duration_seconds": 575
      },
      "Chemistry_000": {
        "score": 9,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Chemistry_000_20260526_205216",
        "cost_usd": 0.8595,
        "duration_seconds": 764
      },
      "Chemistry_001": {
        "score": 6.5,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Chemistry_001_20260526_210513",
        "cost_usd": 0.9045,
        "duration_seconds": 804
      },
      "Chemistry_002": {
        "score": 1,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Chemistry_002_20260526_211856",
        "cost_usd": 0.898875,
        "duration_seconds": 799
      },
      "Earth_000": {
        "score": 25.5,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Earth_000_20260526_220638",
        "cost_usd": 0.795375,
        "duration_seconds": 707
      },
      "Earth_001": {
        "score": 33.19,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Earth_001_20260526_221848",
        "cost_usd": 0.9,
        "duration_seconds": 800
      },
      "Earth_002": {
        "score": 27,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Earth_002_20260527_183331",
        "cost_usd": 0.894375,
        "duration_seconds": 795
      },
      "Earth_003": {
        "score": 10.5,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Earth_003_20260526_224841",
        "cost_usd": 1.39275,
        "duration_seconds": 1238
      },
      "Energy_000": {
        "score": 4.4,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Energy_000_20260527_184722",
        "cost_usd": 0.829125,
        "duration_seconds": 737
      },
      "Energy_001": {
        "score": 21,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Energy_001_20260526_232608",
        "cost_usd": 1.00575,
        "duration_seconds": 894
      },
      "Energy_002": {
        "score": 31.7,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Energy_002_20260526_234126",
        "cost_usd": 1.405125,
        "duration_seconds": 1249
      },
      "Energy_003": {
        "score": 16.3,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Energy_003_20260527_120825",
        "cost_usd": 2.212875,
        "duration_seconds": 1967
      },
      "Information_000": {
        "score": 49.4,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Information_000_20260527_002336",
        "cost_usd": 0.448875,
        "duration_seconds": 399
      },
      "Information_001": {
        "score": 9,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Information_001_20260527_124145",
        "cost_usd": 3.79575,
        "duration_seconds": 3374
      },
      "Information_002": {
        "score": 27.2,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Information_002_20260527_010834",
        "cost_usd": 0.498375,
        "duration_seconds": 443
      },
      "Information_003": {
        "score": 10.8,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Information_003_20260527_011602",
        "cost_usd": 1.672875,
        "duration_seconds": 1487
      },
      "Life_000": {
        "score": 7.7,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Life_000_20260527_185953",
        "cost_usd": 0.552375,
        "duration_seconds": 491
      },
      "Life_001": {
        "score": 12.95,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Life_001_20260527_015452",
        "cost_usd": 0.815625,
        "duration_seconds": 725
      },
      "Life_002": {
        "score": 6.3,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Life_002_20260527_190829",
        "cost_usd": 0.96525,
        "duration_seconds": 858
      },
      "Life_003": {
        "score": 26.5,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Life_003_20260527_022742",
        "cost_usd": 0.390375,
        "duration_seconds": 347
      },
      "Material_000": {
        "score": 22.6,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Material_000_20260527_023350",
        "cost_usd": 1.6155,
        "duration_seconds": 1436
      },
      "Material_001": {
        "score": 0,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Material_001_20260527_025759",
        "cost_usd": 0.5805,
        "duration_seconds": 516
      },
      "Material_002": {
        "score": 40.71,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Material_002_20260527_030652",
        "cost_usd": 2.907,
        "duration_seconds": 2584
      },
      "Material_003": {
        "score": 15.6,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Material_003_20260527_035012",
        "cost_usd": 1.0575,
        "duration_seconds": 940
      },
      "Math_001": {
        "score": 22,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Math_001_20260527_042119",
        "cost_usd": 0.892125,
        "duration_seconds": 793
      },
      "Neuroscience_000": {
        "score": 8,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Neuroscience_000_20260527_051146",
        "cost_usd": 0.986625,
        "duration_seconds": 877
      },
      "Neuroscience_001": {
        "score": 0,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Neuroscience_001_20260527_170712",
        "cost_usd": 2.385,
        "duration_seconds": 2120
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Neuroscience_002_20260527_054624",
        "cost_usd": 0.804375,
        "duration_seconds": 715
      },
      "Neuroscience_003": {
        "score": 0.75,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Neuroscience_003_20260527_055839",
        "cost_usd": 0.943875,
        "duration_seconds": 839
      },
      "Physics_000": {
        "score": 14.5,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Physics_000_20260527_061312",
        "cost_usd": 0.2925,
        "duration_seconds": 260
      },
      "Physics_001": {
        "score": 31.65,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Physics_001_20260527_205419",
        "cost_usd": 1.07325,
        "duration_seconds": 954
      },
      "Physics_003": {
        "score": 34.3,
        "model": "gemini-3.5-flash",
        "model_display": "Gemini-3.5-Flash",
        "run_id": "Physics_003_20260527_064416",
        "cost_usd": 0.837,
        "duration_seconds": 744
      }
    },
    "ResearchHarness (Grok-4.1)": {
      "Astronomy_000": {
        "score": 20,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Astronomy_000_20260414_175140",
        "cost_usd": 0.039783,
        "duration_seconds": 434
      },
      "Astronomy_001": {
        "score": 29.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Astronomy_001_20260414_175938",
        "cost_usd": 0.02695,
        "duration_seconds": 294
      },
      "Astronomy_002": {
        "score": 20.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Astronomy_002_20260414_175938",
        "cost_usd": 0.049317,
        "duration_seconds": 538
      },
      "Astronomy_003": {
        "score": 44.7,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Astronomy_003_20260414_180447",
        "cost_usd": 0.015308,
        "duration_seconds": 167
      },
      "Chemistry_000": {
        "score": 3.8,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Chemistry_000_20260414_180759",
        "cost_usd": 0.029883,
        "duration_seconds": 326
      },
      "Chemistry_001": {
        "score": 1.5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Chemistry_001_20260414_180852",
        "cost_usd": 0.0231,
        "duration_seconds": 252
      },
      "Chemistry_002": {
        "score": 0.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Chemistry_002_20260414_181322",
        "cost_usd": 0.019617,
        "duration_seconds": 214
      },
      "Chemistry_003": {
        "score": 6,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Chemistry_003_20260414_181341",
        "cost_usd": 0.055825,
        "duration_seconds": 609
      },
      "Earth_000": {
        "score": 11.9,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Earth_000_20260414_205103",
        "cost_usd": 0.014483,
        "duration_seconds": 158
      },
      "Earth_001": {
        "score": 30.78,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Earth_001_20260414_205105",
        "cost_usd": 0.021633,
        "duration_seconds": 236
      },
      "Earth_002": {
        "score": 13.6,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Earth_002_20260414_205407",
        "cost_usd": 0.038042,
        "duration_seconds": 415
      },
      "Earth_003": {
        "score": 3.5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Earth_003_20260415_112001",
        "cost_usd": 0.01925,
        "duration_seconds": 210
      },
      "Energy_000": {
        "score": 2.3,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Energy_000_20260414_205947",
        "cost_usd": 0.038408,
        "duration_seconds": 419
      },
      "Energy_001": {
        "score": 8,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Energy_001_20260414_210132",
        "cost_usd": 0.037308,
        "duration_seconds": 407
      },
      "Energy_002": {
        "score": 28.2,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Energy_002_20260414_210702",
        "cost_usd": 0.033092,
        "duration_seconds": 361
      },
      "Energy_003": {
        "score": 6,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Energy_003_20260414_210838",
        "cost_usd": 0.05335,
        "duration_seconds": 582
      },
      "Information_000": {
        "score": 25.5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Information_000_20260414_211319",
        "cost_usd": 0.031258,
        "duration_seconds": 341
      },
      "Information_001": {
        "score": 5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Information_001_20260414_211837",
        "cost_usd": 0.033092,
        "duration_seconds": 361
      },
      "Information_002": {
        "score": 10.8,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Information_002_20260414_211914",
        "cost_usd": 0.020625,
        "duration_seconds": 225
      },
      "Information_003": {
        "score": 6.2,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Information_003_20260414_212308",
        "cost_usd": 0.033,
        "duration_seconds": 360
      },
      "Life_000": {
        "score": 0.5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Life_000_20260414_212517",
        "cost_usd": 0.025208,
        "duration_seconds": 275
      },
      "Life_001": {
        "score": 13.7,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Life_001_20260414_212921",
        "cost_usd": 0.022733,
        "duration_seconds": 248
      },
      "Life_002": {
        "score": 2,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Life_002_20260414_213014",
        "cost_usd": 0.0363,
        "duration_seconds": 396
      },
      "Life_003": {
        "score": 36.5,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Life_003_20260414_213353",
        "cost_usd": 0.023558,
        "duration_seconds": 257
      },
      "Material_000": {
        "score": 16.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Material_000_20260414_213659",
        "cost_usd": 0.057292,
        "duration_seconds": 625
      },
      "Material_001": {
        "score": 11.55,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Material_001_20260415_112001",
        "cost_usd": 0.033,
        "duration_seconds": 360
      },
      "Material_002": {
        "score": 0.66,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Material_002_20260414_213934",
        "cost_usd": 0.034283,
        "duration_seconds": 374
      },
      "Material_003": {
        "score": 9.2,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Material_003_20260414_214604",
        "cost_usd": 0.034467,
        "duration_seconds": 376
      },
      "Math_000": {
        "score": 7.7,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Math_000_20260415_112001",
        "cost_usd": 0.033,
        "duration_seconds": 360
      },
      "Math_001": {
        "score": 26.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Math_001_20260414_214828",
        "cost_usd": 0.02475,
        "duration_seconds": 270
      },
      "Math_002": {
        "score": 2.6,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Math_002_20260414_215242",
        "cost_usd": 0.04125,
        "duration_seconds": 450
      },
      "Neuroscience_000": {
        "score": 8.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Neuroscience_000_20260414_215537",
        "cost_usd": 0.079842,
        "duration_seconds": 871
      },
      "Neuroscience_001": {
        "score": 4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Neuroscience_001_20260414_220041",
        "cost_usd": 0.0297,
        "duration_seconds": 324
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Neuroscience_002_20260415_112044",
        "cost_usd": 0.028233,
        "duration_seconds": 308
      },
      "Neuroscience_003": {
        "score": 6.75,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Neuroscience_003_20260414_221036",
        "cost_usd": 0.074708,
        "duration_seconds": 815
      },
      "Physics_000": {
        "score": 15.4,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Physics_000_20260414_222311",
        "cost_usd": 0.018517,
        "duration_seconds": 202
      },
      "Physics_001": {
        "score": 34.7,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Physics_001_20260414_222500",
        "cost_usd": 0.027225,
        "duration_seconds": 297
      },
      "Physics_002": {
        "score": 11.25,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Physics_002_20260414_222658",
        "cost_usd": 0.102483,
        "duration_seconds": 1118
      },
      "Physics_003": {
        "score": 40.9,
        "model": "Grok-4.1",
        "model_display": "Grok-4.1",
        "run_id": "Physics_003_20260414_223016",
        "cost_usd": 0.033917,
        "duration_seconds": 370
      }
    },
    "ResearchHarness (Grok-4.3)": {
      "Astronomy_001": {
        "score": 7.2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Astronomy_001_20260515_164154",
        "cost_usd": 0.141146,
        "duration_seconds": 271
      },
      "Astronomy_002": {
        "score": 20.6,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Astronomy_002_20260515_164632",
        "cost_usd": 0.661979,
        "duration_seconds": 1271
      },
      "Astronomy_003": {
        "score": 46.4,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Astronomy_003_20260515_170759",
        "cost_usd": 0.107813,
        "duration_seconds": 207
      },
      "Chemistry_000": {
        "score": 13.3,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Chemistry_000_20260515_171134",
        "cost_usd": 0.802083,
        "duration_seconds": 1540
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Chemistry_001_20260518_003544",
        "cost_usd": 0.85,
        "duration_seconds": 1632
      },
      "Chemistry_002": {
        "score": 0,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Chemistry_002_20260515_181127",
        "cost_usd": 0.3375,
        "duration_seconds": 648
      },
      "Chemistry_003": {
        "score": 0.3,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Chemistry_003_20260515_182224",
        "cost_usd": 0.298438,
        "duration_seconds": 573
      },
      "Earth_000": {
        "score": 11.9,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Earth_000_20260515_183205",
        "cost_usd": 0.172396,
        "duration_seconds": 331
      },
      "Earth_001": {
        "score": 35.56,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Earth_001_20260515_183747",
        "cost_usd": 0.273438,
        "duration_seconds": 525
      },
      "Earth_002": {
        "score": 13,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Earth_002_20260515_184648",
        "cost_usd": 0.178646,
        "duration_seconds": 343
      },
      "Earth_003": {
        "score": 0,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Earth_003_20260515_185243",
        "cost_usd": 0.71875,
        "duration_seconds": 1380
      },
      "Energy_000": {
        "score": 14.5,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Energy_000_20260515_191600",
        "cost_usd": 0.654167,
        "duration_seconds": 1256
      },
      "Energy_002": {
        "score": 33.35,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Energy_002_20260518_013609",
        "cost_usd": 0.108333,
        "duration_seconds": 208
      },
      "Energy_003": {
        "score": 8.7,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Energy_003_20260515_211305",
        "cost_usd": 0.143229,
        "duration_seconds": 275
      },
      "Information_000": {
        "score": 2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Information_000_20260515_211758",
        "cost_usd": 0.172917,
        "duration_seconds": 332
      },
      "Information_001": {
        "score": 3.6,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Information_001_20260515_212339",
        "cost_usd": 0.341146,
        "duration_seconds": 655
      },
      "Information_002": {
        "score": 1.8,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Information_002_20260515_213501",
        "cost_usd": 0.128646,
        "duration_seconds": 247
      },
      "Information_003": {
        "score": 2.65,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Information_003_20260515_213914",
        "cost_usd": 0.445833,
        "duration_seconds": 856
      },
      "Life_000": {
        "score": 4.35,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Life_000_20260515_215342",
        "cost_usd": 0.292187,
        "duration_seconds": 561
      },
      "Life_001": {
        "score": 11.05,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Life_001_20260515_220315",
        "cost_usd": 0.463021,
        "duration_seconds": 889
      },
      "Life_002": {
        "score": 5.5,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Life_002_20260515_221819",
        "cost_usd": 0.201042,
        "duration_seconds": 386
      },
      "Life_003": {
        "score": 29,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Life_003_20260515_222450",
        "cost_usd": 0.315625,
        "duration_seconds": 606
      },
      "Material_000": {
        "score": 20.9,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Material_000_20260515_223508",
        "cost_usd": 0.301042,
        "duration_seconds": 578
      },
      "Material_001": {
        "score": 6.85,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Material_001_20260515_224500",
        "cost_usd": 0.153125,
        "duration_seconds": 294
      },
      "Material_002": {
        "score": 16.98,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Material_002_20260515_225003",
        "cost_usd": 1.691667,
        "duration_seconds": 3248
      },
      "Material_003": {
        "score": 4.65,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Material_003_20260518_013948",
        "cost_usd": 0.253646,
        "duration_seconds": 487
      },
      "Math_000": {
        "score": 6.2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Math_000_20260516_021645",
        "cost_usd": 0.123438,
        "duration_seconds": 237
      },
      "Math_001": {
        "score": 13.8,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Math_001_20260516_022047",
        "cost_usd": 0.938021,
        "duration_seconds": 1801
      },
      "Math_002": {
        "score": 2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Math_002_20260516_025058",
        "cost_usd": 0.326562,
        "duration_seconds": 627
      },
      "Math_003": {
        "score": 12,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Math_003_20260516_030137",
        "cost_usd": 0.102083,
        "duration_seconds": 196
      },
      "Neuroscience_000": {
        "score": 6,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Neuroscience_000_20260516_030457",
        "cost_usd": 0.095833,
        "duration_seconds": 184
      },
      "Neuroscience_001": {
        "score": 1.2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Neuroscience_001_20260516_030812",
        "cost_usd": 4.466667,
        "duration_seconds": 8576
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Neuroscience_002_20260516_053119",
        "cost_usd": 0.080729,
        "duration_seconds": 155
      },
      "Neuroscience_003": {
        "score": 3.2,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Neuroscience_003_20260516_053408",
        "cost_usd": 0.038021,
        "duration_seconds": 73
      },
      "Physics_000": {
        "score": 35.7,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Physics_000_20260516_053530",
        "cost_usd": 0.08125,
        "duration_seconds": 156
      },
      "Physics_001": {
        "score": 17.95,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Physics_001_20260516_053817",
        "cost_usd": 0.107292,
        "duration_seconds": 206
      },
      "Physics_002": {
        "score": 19,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Physics_002_20260516_054156",
        "cost_usd": 0.05,
        "duration_seconds": 96
      },
      "Physics_003": {
        "score": 40,
        "model": "Grok-4.3",
        "model_display": "Grok-4.3",
        "run_id": "Physics_003_20260516_054345",
        "cost_usd": 0.035937,
        "duration_seconds": 69
      }
    },
    "ResearchHarness (Hy3-Preview)": {
      "Astronomy_001": {
        "score": 15.2,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Astronomy_001_20260708_165843_278d8aa8",
        "cost_usd": 0.015827,
        "duration_seconds": 476
      },
      "Astronomy_002": {
        "score": 12,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Astronomy_002_20260708_165843_78ab16b8",
        "cost_usd": 0.019617,
        "duration_seconds": 590
      },
      "Chemistry_000": {
        "score": 25.6,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Chemistry_000_20260708_170406_3bc5f433",
        "cost_usd": 0.057655,
        "duration_seconds": 1734
      },
      "Chemistry_001": {
        "score": 7.25,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Chemistry_001_20260708_170538_de35de49",
        "cost_usd": 0.029659,
        "duration_seconds": 892
      },
      "Chemistry_002": {
        "score": 0.3,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Chemistry_002_20260708_170649_6fd05df0",
        "cost_usd": 0.012535,
        "duration_seconds": 377
      },
      "Chemistry_003": {
        "score": 27.3,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Chemistry_003_20260708_170840_dfd22068",
        "cost_usd": 0.039268,
        "duration_seconds": 1181
      },
      "Earth_000": {
        "score": 22.6,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Earth_000_20260708_171329_306e1f79",
        "cost_usd": 0.025935,
        "duration_seconds": 780
      },
      "Earth_001": {
        "score": 28.97,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Earth_001_20260708_172050_8a972df8",
        "cost_usd": 0.024372,
        "duration_seconds": 733
      },
      "Earth_002": {
        "score": 5.4,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Earth_002_20260708_172701_7f28ca80",
        "cost_usd": 0.04256,
        "duration_seconds": 1280
      },
      "Earth_003": {
        "score": 0,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Earth_003_20260708_172842_a56b363f",
        "cost_usd": 0.036475,
        "duration_seconds": 1097
      },
      "Energy_001": {
        "score": 5,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Energy_001_20260708_173321_88362dbb",
        "cost_usd": 0.038238,
        "duration_seconds": 1150
      },
      "Energy_002": {
        "score": 28.2,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Energy_002_20260708_174523_fb52fae6",
        "cost_usd": 0.023375,
        "duration_seconds": 703
      },
      "Energy_003": {
        "score": 0,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Energy_003_20260708_174751_2e8a5c8a",
        "cost_usd": 0.024139,
        "duration_seconds": 726
      },
      "Information_002": {
        "score": 17.5,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Information_002_20260708_175250_6a65d1d0",
        "cost_usd": 0.015694,
        "duration_seconds": 472
      },
      "Information_003": {
        "score": 10.9,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Information_003_20260708_175429_d4bc18b0",
        "cost_usd": 0.030291,
        "duration_seconds": 911
      },
      "Life_000": {
        "score": 6.8,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Life_000_20260708_175723_77b4ec01",
        "cost_usd": 0.026434,
        "duration_seconds": 795
      },
      "Life_001": {
        "score": 5.25,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Life_001_20260708_180037_a447d63c",
        "cost_usd": 0.013233,
        "duration_seconds": 398
      },
      "Life_002": {
        "score": 1,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Life_002_20260708_180049_3b003acb",
        "cost_usd": 0.016592,
        "duration_seconds": 499
      },
      "Life_003": {
        "score": 29,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Life_003_20260708_180744_edd4647c",
        "cost_usd": 0.014829,
        "duration_seconds": 446
      },
      "Material_000": {
        "score": 3.9,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Material_000_20260708_180912_4e9abad9",
        "cost_usd": 0.044621,
        "duration_seconds": 1342
      },
      "Material_001": {
        "score": 14,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Material_001_20260708_180959_7fd7ca70",
        "cost_usd": 0.017589,
        "duration_seconds": 529
      },
      "Material_002": {
        "score": 37.44,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Material_002_20260708_181056_f92a2d80",
        "cost_usd": 0.015029,
        "duration_seconds": 452
      },
      "Material_003": {
        "score": 11.25,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Material_003_20260708_181529_fc2888d3",
        "cost_usd": 0.028163,
        "duration_seconds": 847
      },
      "Math_000": {
        "score": 25,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Math_000_20260708_181845_dfc7ec4b",
        "cost_usd": 0.024173,
        "duration_seconds": 727
      },
      "Math_002": {
        "score": 0,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Math_002_20260708_182421_149f8354",
        "cost_usd": 0.036475,
        "duration_seconds": 1097
      },
      "Math_003": {
        "score": 0,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Math_003_20260708_183010_b17443f8",
        "cost_usd": 0.026434,
        "duration_seconds": 795
      },
      "Neuroscience_000": {
        "score": 1,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Neuroscience_000_20260708_183104_876c9b50",
        "cost_usd": 0.031887,
        "duration_seconds": 959
      },
      "Neuroscience_001": {
        "score": 0.75,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Neuroscience_001_20260708_183148_ea9ee056",
        "cost_usd": 0.042028,
        "duration_seconds": 1264
      },
      "Neuroscience_002": {
        "score": 0.75,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Neuroscience_002_20260708_184247_f0b4d42c",
        "cost_usd": 0.037473,
        "duration_seconds": 1127
      },
      "Neuroscience_003": {
        "score": 3.3,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Neuroscience_003_20260708_184328_86d0efc6",
        "cost_usd": 0.053333,
        "duration_seconds": 1604
      },
      "Physics_000": {
        "score": 21.2,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Physics_000_20260708_184746_42949838",
        "cost_usd": 0.013267,
        "duration_seconds": 399
      },
      "Physics_001": {
        "score": 33.75,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Physics_001_20260708_185324_9c38dfa2",
        "cost_usd": 0.017656,
        "duration_seconds": 531
      },
      "Physics_002": {
        "score": 24.35,
        "model": "hy3-preview",
        "model_display": "Hy3-Preview",
        "run_id": "cli_Physics_002_20260708_185447_c1a1fe6f",
        "cost_usd": 0.046217,
        "duration_seconds": 1390
      }
    },
    "ResearchHarness (Kimi-K2.5)": {
      "Astronomy_000": {
        "score": 14.4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Astronomy_000_20260415_115142",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Astronomy_001": {
        "score": 21.2,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Astronomy_001_20260415_115142",
        "cost_usd": 0.2596,
        "duration_seconds": 649
      },
      "Astronomy_002": {
        "score": 11,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Astronomy_002_20260415_115310",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Astronomy_003": {
        "score": 46.8,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Astronomy_003_20260415_120217",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Chemistry_000": {
        "score": 18.9,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Chemistry_000_20260415_120315",
        "cost_usd": 1.0448,
        "duration_seconds": 2612
      },
      "Chemistry_001": {
        "score": 3.55,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Chemistry_001_20260415_120942",
        "cost_usd": 0.7088,
        "duration_seconds": 1772
      },
      "Chemistry_002": {
        "score": 1.2,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Chemistry_002_20260415_123938",
        "cost_usd": 0.2372,
        "duration_seconds": 593
      },
      "Chemistry_003": {
        "score": 6.9,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Chemistry_003_20260415_124720",
        "cost_usd": 0.2052,
        "duration_seconds": 513
      },
      "Earth_000": {
        "score": 15.8,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Earth_000_20260415_125003",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Earth_001": {
        "score": 21.06,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Earth_001_20260415_125648",
        "cost_usd": 0.232,
        "duration_seconds": 580
      },
      "Earth_002": {
        "score": 25.2,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Earth_002_20260415_130601",
        "cost_usd": 0.334,
        "duration_seconds": 835
      },
      "Earth_003": {
        "score": 3.6,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Earth_003_20260415_130710",
        "cost_usd": 0.342,
        "duration_seconds": 855
      },
      "Energy_000": {
        "score": 5,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Energy_000_20260415_132037",
        "cost_usd": 0.4276,
        "duration_seconds": 1069
      },
      "Energy_001": {
        "score": 3.4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Energy_001_20260415_132153",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Energy_002": {
        "score": 25.3,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Energy_002_20260415_132706",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Energy_003": {
        "score": 19.5,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Energy_003_20260415_133243",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Information_000": {
        "score": 16.4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Information_000_20260415_140033",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Information_001": {
        "score": 7.6,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Information_001_20260415_140033",
        "cost_usd": 0.438,
        "duration_seconds": 1095
      },
      "Information_002": {
        "score": 10.3,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Information_002_20260415_140621",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Information_003": {
        "score": 3.25,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Information_003_20260415_141853",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Life_000": {
        "score": 7.45,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Life_000_20260415_141919",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Life_001": {
        "score": 7.75,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Life_001_20260415_143226",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Life_002": {
        "score": 5,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Life_002_20260415_143514",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Life_003": {
        "score": 25.4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Life_003_20260415_144005",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Material_000": {
        "score": 4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Material_000_20260415_144516",
        "cost_usd": 1.44,
        "duration_seconds": 3600
      },
      "Material_001": {
        "score": 6.3,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Material_001_20260415_150331",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Material_002": {
        "score": 31.15,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Material_002_20260415_150736",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Material_003": {
        "score": 10.95,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Material_003_20260415_153600",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Math_000": {
        "score": 18.3,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Math_000_20260415_154537",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Math_001": {
        "score": 15.2,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Math_001_20260415_155046",
        "cost_usd": 1.44,
        "duration_seconds": 3600
      },
      "Math_002": {
        "score": 14.7,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Math_002_20260415_160729",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Neuroscience_000": {
        "score": 7.4,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Neuroscience_000_20260415_165658",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Neuroscience_001": {
        "score": 0.75,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Neuroscience_001_20260415_170436",
        "cost_usd": 0.4824,
        "duration_seconds": 1206
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Neuroscience_002_20260415_170839",
        "cost_usd": 1.0448,
        "duration_seconds": 2612
      },
      "Neuroscience_003": {
        "score": 3.7,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Neuroscience_003_20260415_172530",
        "cost_usd": 0.4348,
        "duration_seconds": 1087
      },
      "Physics_000": {
        "score": 13.2,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Physics_000_20260415_174439",
        "cost_usd": 0.3052,
        "duration_seconds": 763
      },
      "Physics_001": {
        "score": 32.05,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Physics_001_20260415_175239",
        "cost_usd": 0.6176,
        "duration_seconds": 1544
      },
      "Physics_002": {
        "score": 20.1,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Physics_002_20260415_175755",
        "cost_usd": 0.9224,
        "duration_seconds": 2306
      },
      "Physics_003": {
        "score": 40.5,
        "model": "Kimi-K2.5",
        "model_display": "Kimi-K2.5",
        "run_id": "Physics_003_20260415_181856",
        "cost_usd": 0.3548,
        "duration_seconds": 887
      }
    },
    "ResearchHarness (Kimi-K2.6)": {
      "Astronomy_000": {
        "score": 3.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Astronomy_000_20260518_114619",
        "cost_usd": 1.769013,
        "duration_seconds": 3099
      },
      "Astronomy_001": {
        "score": 36,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Astronomy_001_20260518_123809",
        "cost_usd": 1.392833,
        "duration_seconds": 2440
      },
      "Astronomy_002": {
        "score": 28.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Astronomy_002_20260518_131859",
        "cost_usd": 2.854738,
        "duration_seconds": 5001
      },
      "Astronomy_003": {
        "score": 44,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Astronomy_003_20260518_144228",
        "cost_usd": 0.421846,
        "duration_seconds": 739
      },
      "Chemistry_001": {
        "score": 5.75,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Chemistry_001_20260518_172502",
        "cost_usd": 2.113225,
        "duration_seconds": 3702
      },
      "Chemistry_002": {
        "score": 0.4,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Chemistry_002_20260518_182701",
        "cost_usd": 0.39045,
        "duration_seconds": 684
      },
      "Earth_000": {
        "score": 21.6,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Earth_000_20260518_202022",
        "cost_usd": 1.169638,
        "duration_seconds": 2049
      },
      "Earth_001": {
        "score": 41.65,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Earth_001_20260518_205500",
        "cost_usd": 0.336221,
        "duration_seconds": 589
      },
      "Earth_002": {
        "score": 24.8,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Earth_002_20260518_210503",
        "cost_usd": 0.441254,
        "duration_seconds": 773
      },
      "Earth_003": {
        "score": 3.4,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Earth_003_20260518_211840",
        "cost_usd": 3.029413,
        "duration_seconds": 5307
      },
      "Energy_000": {
        "score": 9.5,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Energy_000_20260518_224729",
        "cost_usd": 1.024075,
        "duration_seconds": 1794
      },
      "Energy_001": {
        "score": 10.4,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Energy_001_20260518_231734",
        "cost_usd": 1.000671,
        "duration_seconds": 1753
      },
      "Energy_002": {
        "score": 31.4,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Energy_002_20260518_234701",
        "cost_usd": 1.170208,
        "duration_seconds": 2050
      },
      "Energy_003": {
        "score": 21,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Energy_003_20260519_002123",
        "cost_usd": 0.200362,
        "duration_seconds": 351
      },
      "Information_000": {
        "score": 0,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Information_000_20260519_002724",
        "cost_usd": 1.741613,
        "duration_seconds": 3051
      },
      "Information_001": {
        "score": 18,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Information_001_20260519_011821",
        "cost_usd": 0.817433,
        "duration_seconds": 1432
      },
      "Information_002": {
        "score": 27.8,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Information_002_20260519_014235",
        "cost_usd": 0.161546,
        "duration_seconds": 283
      },
      "Information_003": {
        "score": 5.25,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Information_003_20260519_094352",
        "cost_usd": 2.351263,
        "duration_seconds": 4119
      },
      "Life_000": {
        "score": 6.8,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Life_000_20260519_105356",
        "cost_usd": 1.1508,
        "duration_seconds": 2016
      },
      "Life_001": {
        "score": 11.55,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Life_001_20260519_112751",
        "cost_usd": 0.361908,
        "duration_seconds": 634
      },
      "Life_002": {
        "score": 2.8,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Life_002_20260519_113839",
        "cost_usd": 0.428696,
        "duration_seconds": 751
      },
      "Life_003": {
        "score": 34.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Life_003_20260519_115113",
        "cost_usd": 0.413854,
        "duration_seconds": 725
      },
      "Material_000": {
        "score": 15.5,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Material_000_20260519_120332",
        "cost_usd": 2.440883,
        "duration_seconds": 4276
      },
      "Material_001": {
        "score": 10.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Material_001_20260519_131456",
        "cost_usd": 0.361908,
        "duration_seconds": 634
      },
      "Material_002": {
        "score": 39.08,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Material_002_20260519_132542",
        "cost_usd": 1.424229,
        "duration_seconds": 2495
      },
      "Material_003": {
        "score": 24.65,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Material_003_20260519_140746",
        "cost_usd": 1.020079,
        "duration_seconds": 1787
      },
      "Math_000": {
        "score": 23.55,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Math_000_20260519_143753",
        "cost_usd": 2.516233,
        "duration_seconds": 4408
      },
      "Math_001": {
        "score": 21.6,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Math_001_20260519_155141",
        "cost_usd": 1.307208,
        "duration_seconds": 2290
      },
      "Math_002": {
        "score": 14,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Math_002_20260519_163350",
        "cost_usd": 1.926563,
        "duration_seconds": 3375
      },
      "Math_003": {
        "score": 18.75,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Math_003_20260519_173023",
        "cost_usd": 2.014471,
        "duration_seconds": 3529
      },
      "Neuroscience_000": {
        "score": 9,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Neuroscience_000_20260519_182920",
        "cost_usd": 1.899733,
        "duration_seconds": 3328
      },
      "Neuroscience_001": {
        "score": 3.5,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Neuroscience_001_20260519_192503",
        "cost_usd": 1.239279,
        "duration_seconds": 2171
      },
      "Neuroscience_002": {
        "score": 0.5,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Neuroscience_002_20260519_200133",
        "cost_usd": 1.1097,
        "duration_seconds": 1944
      },
      "Neuroscience_003": {
        "score": 20.4,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Neuroscience_003_20260519_203414",
        "cost_usd": 0.776333,
        "duration_seconds": 1360
      },
      "Physics_000": {
        "score": 25.6,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Physics_000_20260519_205720",
        "cost_usd": 0.498338,
        "duration_seconds": 873
      },
      "Physics_001": {
        "score": 17,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Physics_001_20260519_211209",
        "cost_usd": 0.812296,
        "duration_seconds": 1423
      },
      "Physics_002": {
        "score": 21.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Physics_002_20260519_213610",
        "cost_usd": 0.356771,
        "duration_seconds": 625
      },
      "Physics_003": {
        "score": 32.1,
        "model": "Kimi-K2.6",
        "model_display": "Kimi-K2.6",
        "run_id": "Physics_003_20260519_214659",
        "cost_usd": 0.687283,
        "duration_seconds": 1204
      }
    },
    "ResearchHarness (MiMo-V2-Pro)": {
      "Astronomy_000": {
        "score": 11.2,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Astronomy_000_20260414_152814",
        "cost_usd": 3.5085,
        "duration_seconds": 7017
      },
      "Astronomy_001": {
        "score": 10,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Astronomy_001_20260414_114811",
        "cost_usd": 0.203,
        "duration_seconds": 406
      },
      "Astronomy_002": {
        "score": 19.1,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Astronomy_002_20260414_154725",
        "cost_usd": 2.047,
        "duration_seconds": 4094
      },
      "Astronomy_003": {
        "score": 46.7,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Astronomy_003_20260414_120359",
        "cost_usd": 0.132,
        "duration_seconds": 264
      },
      "Chemistry_000": {
        "score": 14,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Chemistry_000_20260414_120823",
        "cost_usd": 2.294,
        "duration_seconds": 4588
      },
      "Chemistry_001": {
        "score": 0.75,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Chemistry_001_20260414_132451",
        "cost_usd": 0.192,
        "duration_seconds": 384
      },
      "Chemistry_002": {
        "score": 1,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Chemistry_002_20260414_133115",
        "cost_usd": 0.2525,
        "duration_seconds": 505
      },
      "Chemistry_003": {
        "score": 9.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Chemistry_003_20260414_165658",
        "cost_usd": 1.9945,
        "duration_seconds": 3989
      },
      "Earth_000": {
        "score": 14.7,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Earth_000_20260414_150832",
        "cost_usd": 0.386,
        "duration_seconds": 772
      },
      "Earth_001": {
        "score": 35.57,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Earth_001_20260414_152124",
        "cost_usd": 0.258,
        "duration_seconds": 516
      },
      "Earth_002": {
        "score": 28.1,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Earth_002_20260414_180327",
        "cost_usd": 0.345,
        "duration_seconds": 690
      },
      "Earth_003": {
        "score": 1,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Earth_003_20260414_181457",
        "cost_usd": 0.3365,
        "duration_seconds": 673
      },
      "Energy_000": {
        "score": 12.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Energy_000_20260414_182610",
        "cost_usd": 0.7495,
        "duration_seconds": 1499
      },
      "Energy_001": {
        "score": 9.1,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Energy_001_20260414_185109",
        "cost_usd": 1.059,
        "duration_seconds": 2118
      },
      "Energy_002": {
        "score": 21.9,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Energy_002_20260414_192627",
        "cost_usd": 0.8895,
        "duration_seconds": 1779
      },
      "Energy_003": {
        "score": 7.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Energy_003_20260414_195607",
        "cost_usd": 0.2935,
        "duration_seconds": 587
      },
      "Information_002": {
        "score": 13.2,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Information_002_20260414_213609",
        "cost_usd": 0.1605,
        "duration_seconds": 321
      },
      "Information_003": {
        "score": 5.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Information_003_20260414_214130",
        "cost_usd": 0.7645,
        "duration_seconds": 1529
      },
      "Life_000": {
        "score": 4.9,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Life_000_20260414_220659",
        "cost_usd": 0.323,
        "duration_seconds": 646
      },
      "Life_001": {
        "score": 7.05,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Life_001_20260414_221745",
        "cost_usd": 0.169,
        "duration_seconds": 338
      },
      "Life_002": {
        "score": 6.6,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Life_002_20260414_222323",
        "cost_usd": 0.236,
        "duration_seconds": 472
      },
      "Life_003": {
        "score": 32.6,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Life_003_20260414_223115",
        "cost_usd": 0.198,
        "duration_seconds": 396
      },
      "Material_000": {
        "score": 13.2,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Material_000_20260414_223751",
        "cost_usd": 0.643,
        "duration_seconds": 1286
      },
      "Material_001": {
        "score": 18,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Material_001_20260414_225917",
        "cost_usd": 0.2615,
        "duration_seconds": 523
      },
      "Material_002": {
        "score": 37.31,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Material_002_20260414_230800",
        "cost_usd": 0.337,
        "duration_seconds": 674
      },
      "Material_003": {
        "score": 17,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Material_003_20260414_231914",
        "cost_usd": 0.458,
        "duration_seconds": 916
      },
      "Math_000": {
        "score": 7.2,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Math_000_20260414_091314",
        "cost_usd": 0.3945,
        "duration_seconds": 789
      },
      "Math_001": {
        "score": 33.6,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Math_001_20260414_233431",
        "cost_usd": 0.1665,
        "duration_seconds": 333
      },
      "Math_002": {
        "score": 3.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Math_002_20260414_234004",
        "cost_usd": 1.2055,
        "duration_seconds": 2411
      },
      "Math_003": {
        "score": 10,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Math_003_20260415_002019",
        "cost_usd": 0.3105,
        "duration_seconds": 621
      },
      "Neuroscience_000": {
        "score": 9.2,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Neuroscience_000_20260415_003040",
        "cost_usd": 0.204,
        "duration_seconds": 408
      },
      "Neuroscience_001": {
        "score": 2.7,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Neuroscience_001_20260415_003728",
        "cost_usd": 0.2455,
        "duration_seconds": 491
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Neuroscience_002_20260415_004540",
        "cost_usd": 0.757,
        "duration_seconds": 1514
      },
      "Neuroscience_003": {
        "score": 13.05,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Neuroscience_003_20260415_011054",
        "cost_usd": 0.805,
        "duration_seconds": 1610
      },
      "Physics_000": {
        "score": 17.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Physics_000_20260415_013744",
        "cost_usd": 0.2305,
        "duration_seconds": 461
      },
      "Physics_001": {
        "score": 22.55,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Physics_001_20260415_100406",
        "cost_usd": 0.3545,
        "duration_seconds": 709
      },
      "Physics_002": {
        "score": 22,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Physics_002_20260415_145205",
        "cost_usd": 0.2115,
        "duration_seconds": 423
      },
      "Physics_003": {
        "score": 43.5,
        "model": "MiMo-V2-Pro",
        "model_display": "MiMo-V2-Pro",
        "run_id": "Physics_003_20260415_022350",
        "cost_usd": 0.1685,
        "duration_seconds": 337
      }
    },
    "ResearchHarness (MiMo-V2.5)": {
      "Astronomy_000": {
        "score": 19,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Astronomy_000_20260515_161340",
        "cost_usd": 0.2562,
        "duration_seconds": 915
      },
      "Astronomy_001": {
        "score": 8,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Astronomy_001_20260515_162909",
        "cost_usd": 0.08988,
        "duration_seconds": 321
      },
      "Astronomy_002": {
        "score": 27.5,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Astronomy_002_20260515_163452",
        "cost_usd": 0.26404,
        "duration_seconds": 943
      },
      "Astronomy_003": {
        "score": 43.1,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Astronomy_003_20260515_165041",
        "cost_usd": 0.06188,
        "duration_seconds": 221
      },
      "Chemistry_001": {
        "score": 5.25,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Chemistry_001_20260515_192436",
        "cost_usd": 0.09856,
        "duration_seconds": 352
      },
      "Chemistry_002": {
        "score": 0,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Chemistry_002_20260515_193045",
        "cost_usd": 0.08596,
        "duration_seconds": 307
      },
      "Chemistry_003": {
        "score": 8,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Chemistry_003_20260515_193607",
        "cost_usd": 0.26348,
        "duration_seconds": 941
      },
      "Earth_000": {
        "score": 15.2,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Earth_000_20260515_195158",
        "cost_usd": 0.12292,
        "duration_seconds": 439
      },
      "Earth_001": {
        "score": 22.54,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Earth_001_20260515_195931",
        "cost_usd": 0.0854,
        "duration_seconds": 305
      },
      "Earth_002": {
        "score": 25.9,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Earth_002_20260515_200447",
        "cost_usd": 0.11928,
        "duration_seconds": 426
      },
      "Earth_003": {
        "score": 0,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Earth_003_20260515_201206",
        "cost_usd": 0.6006,
        "duration_seconds": 2145
      },
      "Energy_000": {
        "score": 14.7,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Energy_000_20260518_000259",
        "cost_usd": 0.32144,
        "duration_seconds": 1148
      },
      "Energy_001": {
        "score": 23.4,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Energy_001_20260518_002218",
        "cost_usd": 0.12992,
        "duration_seconds": 464
      },
      "Energy_002": {
        "score": 23.7,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Energy_002_20260518_003015",
        "cost_usd": 0.16772,
        "duration_seconds": 599
      },
      "Energy_003": {
        "score": 16.3,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Energy_003_20260518_004025",
        "cost_usd": 0.0896,
        "duration_seconds": 320
      },
      "Information_000": {
        "score": 16.7,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Information_000_20260518_004600",
        "cost_usd": 0.44744,
        "duration_seconds": 1598
      },
      "Information_001": {
        "score": 1,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Information_001_20260518_011248",
        "cost_usd": 0.441,
        "duration_seconds": 1575
      },
      "Information_002": {
        "score": 26.9,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Information_002_20260518_013922",
        "cost_usd": 0.056,
        "duration_seconds": 200
      },
      "Information_003": {
        "score": 4.6,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Information_003_20260518_014248",
        "cost_usd": 1.83232,
        "duration_seconds": 6544
      },
      "Life_000": {
        "score": 4.75,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Life_000_20260518_033206",
        "cost_usd": 0.11452,
        "duration_seconds": 409
      },
      "Life_001": {
        "score": 11.95,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Life_001_20260518_033906",
        "cost_usd": 0.056,
        "duration_seconds": 200
      },
      "Life_002": {
        "score": 3.5,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Life_002_20260518_034243",
        "cost_usd": 0.13888,
        "duration_seconds": 496
      },
      "Life_003": {
        "score": 30.9,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Life_003_20260518_035105",
        "cost_usd": 0.06524,
        "duration_seconds": 233
      },
      "Material_000": {
        "score": 23.5,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Material_000_20260518_035508",
        "cost_usd": 0.45052,
        "duration_seconds": 1609
      },
      "Material_001": {
        "score": 7,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Material_001_20260518_042207",
        "cost_usd": 0.06244,
        "duration_seconds": 223
      },
      "Material_002": {
        "score": 28.5,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Material_002_20260518_042559",
        "cost_usd": 0.06132,
        "duration_seconds": 219
      },
      "Material_003": {
        "score": 17.7,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Material_003_20260518_042948",
        "cost_usd": 0.13132,
        "duration_seconds": 469
      },
      "Math_000": {
        "score": 18.5,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Math_000_20260518_043746",
        "cost_usd": 0.22064,
        "duration_seconds": 788
      },
      "Math_001": {
        "score": 30.2,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Math_001_20260518_045107",
        "cost_usd": 0.21,
        "duration_seconds": 750
      },
      "Math_002": {
        "score": 14.1,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Math_002_20260518_050356",
        "cost_usd": 0.3766,
        "duration_seconds": 1345
      },
      "Math_003": {
        "score": 10,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Math_003_20260518_052635",
        "cost_usd": 0.11116,
        "duration_seconds": 397
      },
      "Neuroscience_000": {
        "score": 3.6,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Neuroscience_000_20260518_053316",
        "cost_usd": 0.1862,
        "duration_seconds": 665
      },
      "Neuroscience_001": {
        "score": 1.25,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Neuroscience_001_20260518_054434",
        "cost_usd": 0.1274,
        "duration_seconds": 455
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Neuroscience_002_20260518_055222",
        "cost_usd": 0.34216,
        "duration_seconds": 1222
      },
      "Neuroscience_003": {
        "score": 12.75,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Neuroscience_003_20260518_061256",
        "cost_usd": 0.11928,
        "duration_seconds": 426
      },
      "Physics_000": {
        "score": 27.4,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Physics_000_20260518_062014",
        "cost_usd": 0.08036,
        "duration_seconds": 287
      },
      "Physics_001": {
        "score": 46.25,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Physics_001_20260518_062515",
        "cost_usd": 0.40936,
        "duration_seconds": 1462
      },
      "Physics_002": {
        "score": 29,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Physics_002_20260518_064947",
        "cost_usd": 0.07644,
        "duration_seconds": 273
      },
      "Physics_003": {
        "score": 36,
        "model": "MiMo-V2.5",
        "model_display": "MiMo-V2.5",
        "run_id": "Physics_003_20260518_065440",
        "cost_usd": 0.07504,
        "duration_seconds": 268
      }
    },
    "ResearchHarness (MiniMax-M3)": {
      "Astronomy_000": {
        "score": 11.9,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Astronomy_000_20260605_155354",
        "cost_usd": 0.368025,
        "duration_seconds": 2103
      },
      "Astronomy_001": {
        "score": 37.2,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Astronomy_001_20260605_165042",
        "cost_usd": 0.19005,
        "duration_seconds": 1086
      },
      "Astronomy_002": {
        "score": 26,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Astronomy_002_20260605_173325",
        "cost_usd": 0.357875,
        "duration_seconds": 2045
      },
      "Astronomy_003": {
        "score": 47.1,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Astronomy_003_20260605_180742",
        "cost_usd": 0.072275,
        "duration_seconds": 413
      },
      "Chemistry_000": {
        "score": 18.05,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Chemistry_000_20260605_181446",
        "cost_usd": 1.44095,
        "duration_seconds": 8234
      },
      "Chemistry_001": {
        "score": 9.35,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Chemistry_001_20260605_203208",
        "cost_usd": 0.57995,
        "duration_seconds": 3314
      },
      "Chemistry_002": {
        "score": 0,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Chemistry_002_20260605_212733",
        "cost_usd": 0.503475,
        "duration_seconds": 2877
      },
      "Chemistry_003": {
        "score": 20.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Chemistry_003_20260605_221544",
        "cost_usd": 0.929425,
        "duration_seconds": 5311
      },
      "Earth_000": {
        "score": 24.2,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Earth_000_20260605_234433",
        "cost_usd": 0.243075,
        "duration_seconds": 1389
      },
      "Earth_001": {
        "score": 36.58,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Earth_001_20260606_000800",
        "cost_usd": 0.135625,
        "duration_seconds": 775
      },
      "Earth_002": {
        "score": 12.6,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Earth_002_20260606_002108",
        "cost_usd": 0.232925,
        "duration_seconds": 1331
      },
      "Earth_003": {
        "score": 1.5,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Earth_003_20260606_004333",
        "cost_usd": 0.825475,
        "duration_seconds": 4717
      },
      "Energy_000": {
        "score": 16,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Energy_000_20260606_020226",
        "cost_usd": 0.70735,
        "duration_seconds": 4042
      },
      "Energy_001": {
        "score": 22,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Energy_001_20260606_031000",
        "cost_usd": 0.296975,
        "duration_seconds": 1697
      },
      "Energy_002": {
        "score": 30.85,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Energy_002_20260606_033828",
        "cost_usd": 0.2303,
        "duration_seconds": 1316
      },
      "Energy_003": {
        "score": 27,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Energy_003_20260606_040037",
        "cost_usd": 0.193725,
        "duration_seconds": 1107
      },
      "Information_001": {
        "score": 3.6,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Information_001_20260606_041949",
        "cost_usd": 0.59745,
        "duration_seconds": 3414
      },
      "Information_002": {
        "score": 21,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Information_002_20260606_051658",
        "cost_usd": 0.12705,
        "duration_seconds": 726
      },
      "Information_003": {
        "score": 15.1,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Information_003_20260606_052909",
        "cost_usd": 0.438025,
        "duration_seconds": 2503
      },
      "Life_000": {
        "score": 13.2,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Life_000_20260606_061104",
        "cost_usd": 0.5656,
        "duration_seconds": 3232
      },
      "Life_001": {
        "score": 0,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Life_001_20260606_070601",
        "cost_usd": 0.246225,
        "duration_seconds": 1407
      },
      "Life_002": {
        "score": 6,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Life_002_20260606_072940",
        "cost_usd": 0.24255,
        "duration_seconds": 1386
      },
      "Life_003": {
        "score": 31.6,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Life_003_20260606_075251",
        "cost_usd": 0.287,
        "duration_seconds": 1640
      },
      "Material_000": {
        "score": 21.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Material_000_20260606_082023",
        "cost_usd": 0.81655,
        "duration_seconds": 4666
      },
      "Material_001": {
        "score": 11.55,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Material_001_20260606_093819",
        "cost_usd": 0.151725,
        "duration_seconds": 867
      },
      "Material_002": {
        "score": 27.87,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Material_002_20260606_095257",
        "cost_usd": 0.6426,
        "duration_seconds": 3672
      },
      "Material_003": {
        "score": 8.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Material_003_20260608_111359",
        "cost_usd": 0.6692,
        "duration_seconds": 3824
      },
      "Math_000": {
        "score": 19.55,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Math_000_20260608_121809",
        "cost_usd": 0.3304,
        "duration_seconds": 1888
      },
      "Math_001": {
        "score": 38.8,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Math_001_20260608_124949",
        "cost_usd": 0.72625,
        "duration_seconds": 4150
      },
      "Math_002": {
        "score": 20.1,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Math_002_20260608_135908",
        "cost_usd": 0.599025,
        "duration_seconds": 3423
      },
      "Math_003": {
        "score": 8.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Math_003_20260608_145625",
        "cost_usd": 0.955675,
        "duration_seconds": 5461
      },
      "Neuroscience_000": {
        "score": 11.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Neuroscience_000_20260608_162730",
        "cost_usd": 0.386575,
        "duration_seconds": 2209
      },
      "Neuroscience_002": {
        "score": 1,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Neuroscience_002_20260608_170620",
        "cost_usd": 0.28455,
        "duration_seconds": 1626
      },
      "Neuroscience_003": {
        "score": 13.2,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Neuroscience_003_20260608_173341",
        "cost_usd": 0.694925,
        "duration_seconds": 3971
      },
      "Physics_000": {
        "score": 27.6,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Physics_000_20260608_184005",
        "cost_usd": 0.319025,
        "duration_seconds": 1823
      },
      "Physics_001": {
        "score": 31.9,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Physics_001_20260608_191041",
        "cost_usd": 0.14035,
        "duration_seconds": 802
      },
      "Physics_002": {
        "score": 43.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Physics_002_20260608_192417",
        "cost_usd": 0.237475,
        "duration_seconds": 1357
      },
      "Physics_003": {
        "score": 37.4,
        "model": "MiniMax-M3",
        "model_display": "MiniMax-M3",
        "run_id": "Physics_003_20260608_194709",
        "cost_usd": 0.288925,
        "duration_seconds": 1651
      }
    },
    "ResearchHarness (Qwen3.5-397B-A17B)": {
      "Astronomy_000": {
        "score": 11.1,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Astronomy_000_20260416_152811",
        "cost_usd": 0.4257,
        "duration_seconds": 946
      },
      "Astronomy_001": {
        "score": 8,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Astronomy_001_20260416_152811",
        "cost_usd": 0.20835,
        "duration_seconds": 463
      },
      "Astronomy_002": {
        "score": 3.1,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Astronomy_002_20260416_153612",
        "cost_usd": 0.67725,
        "duration_seconds": 1505
      },
      "Astronomy_003": {
        "score": 46.4,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Astronomy_003_20260416_154412",
        "cost_usd": 0.3438,
        "duration_seconds": 764
      },
      "Chemistry_000": {
        "score": 20.4,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Chemistry_000_20260416_155726",
        "cost_usd": 1.2915,
        "duration_seconds": 2870
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Chemistry_001_20260416_160135",
        "cost_usd": 0.66015,
        "duration_seconds": 1467
      },
      "Chemistry_002": {
        "score": 3.6,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Chemistry_002_20260416_162621",
        "cost_usd": 0.18855,
        "duration_seconds": 419
      },
      "Chemistry_003": {
        "score": 6.9,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Chemistry_003_20260416_163347",
        "cost_usd": 0.64575,
        "duration_seconds": 1435
      },
      "Earth_000": {
        "score": 15.6,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Earth_000_20260416_164538",
        "cost_usd": 0.4365,
        "duration_seconds": 970
      },
      "Earth_001": {
        "score": 35.58,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Earth_001_20260416_165809",
        "cost_usd": 0.35145,
        "duration_seconds": 781
      },
      "Earth_002": {
        "score": 18.6,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Earth_002_20260416_170232",
        "cost_usd": 0.37305,
        "duration_seconds": 829
      },
      "Earth_003": {
        "score": 3.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Earth_003_20260416_171139",
        "cost_usd": 0.50265,
        "duration_seconds": 1117
      },
      "Energy_000": {
        "score": 16.9,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Energy_000_20260416_171718",
        "cost_usd": 0.82845,
        "duration_seconds": 1841
      },
      "Energy_001": {
        "score": 10.6,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Energy_001_20260416_173052",
        "cost_usd": 0.4797,
        "duration_seconds": 1066
      },
      "Energy_002": {
        "score": 31.55,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Energy_002_20260416_174825",
        "cost_usd": 0.3105,
        "duration_seconds": 690
      },
      "Energy_003": {
        "score": 15.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Energy_003_20260416_174903",
        "cost_usd": 0.4797,
        "duration_seconds": 1066
      },
      "Information_000": {
        "score": 9.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Information_000_20260416_174938",
        "cost_usd": 0.2151,
        "duration_seconds": 478
      },
      "Information_001": {
        "score": 6.4,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Information_001_20260416_175758",
        "cost_usd": 0.11205,
        "duration_seconds": 249
      },
      "Information_002": {
        "score": 7.2,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Information_002_20260416_180020",
        "cost_usd": 0.1917,
        "duration_seconds": 426
      },
      "Information_003": {
        "score": 0.75,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Information_003_20260416_180247",
        "cost_usd": 1.20555,
        "duration_seconds": 2679
      },
      "Life_000": {
        "score": 4.8,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Life_000_20260416_180742",
        "cost_usd": 0.23445,
        "duration_seconds": 521
      },
      "Life_001": {
        "score": 10.75,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Life_001_20260416_181657",
        "cost_usd": 0.24885,
        "duration_seconds": 553
      },
      "Life_002": {
        "score": 6.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Life_002_20260416_182642",
        "cost_usd": 0.39555,
        "duration_seconds": 879
      },
      "Life_003": {
        "score": 23.8,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Life_003_20260416_184145",
        "cost_usd": 0.5868,
        "duration_seconds": 1304
      },
      "Material_000": {
        "score": 14,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Material_000_20260416_184755",
        "cost_usd": 1.62,
        "duration_seconds": 3600
      },
      "Material_001": {
        "score": 17.1,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Material_001_20260416_190409",
        "cost_usd": 0.4608,
        "duration_seconds": 1024
      },
      "Material_002": {
        "score": 33.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Material_002_20260416_192151",
        "cost_usd": 0.2133,
        "duration_seconds": 474
      },
      "Material_003": {
        "score": 8.9,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Material_003_20260416_193039",
        "cost_usd": 1.47285,
        "duration_seconds": 3273
      },
      "Math_000": {
        "score": 23.1,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Math_000_20260416_194756",
        "cost_usd": 0.4635,
        "duration_seconds": 1030
      },
      "Math_001": {
        "score": 30.4,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Math_001_20260416_200558",
        "cost_usd": 1.62,
        "duration_seconds": 3600
      },
      "Math_002": {
        "score": 3.5,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Math_002_20260416_202559",
        "cost_usd": 0.7929,
        "duration_seconds": 1762
      },
      "Math_003": {
        "score": 0,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Math_003_20260416_205639",
        "cost_usd": 0.396,
        "duration_seconds": 880
      },
      "Neuroscience_000": {
        "score": 11.4,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Neuroscience_000_20260416_210559",
        "cost_usd": 0.3411,
        "duration_seconds": 758
      },
      "Neuroscience_001": {
        "score": 1.25,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Neuroscience_001_20260416_211156",
        "cost_usd": 0.4959,
        "duration_seconds": 1102
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Neuroscience_002_20260416_211933",
        "cost_usd": 0.87705,
        "duration_seconds": 1949
      },
      "Neuroscience_003": {
        "score": 4.05,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Neuroscience_003_20260416_213123",
        "cost_usd": 1.01475,
        "duration_seconds": 2255
      },
      "Physics_000": {
        "score": 20.9,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Physics_000_20260416_215341",
        "cost_usd": 0.49185,
        "duration_seconds": 1093
      },
      "Physics_001": {
        "score": 25.8,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Physics_001_20260416_221052",
        "cost_usd": 0.5247,
        "duration_seconds": 1166
      },
      "Physics_002": {
        "score": 19.55,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Physics_002_20260416_221313",
        "cost_usd": 0.44595,
        "duration_seconds": 991
      },
      "Physics_003": {
        "score": 38.3,
        "model": "Qwen3.5-397B-A17B",
        "model_display": "Qwen3.5-397B-A17B",
        "run_id": "Physics_003_20260416_223115",
        "cost_usd": 0.44325,
        "duration_seconds": 985
      }
    },
    "ResearchHarness (Qwen3.6-Plus)": {
      "Astronomy_000": {
        "score": 21,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Astronomy_000_20260414_215221",
        "cost_usd": 0.614625,
        "duration_seconds": 1639
      },
      "Astronomy_001": {
        "score": 35.2,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Astronomy_001_20260414_221941",
        "cost_usd": 0.6705,
        "duration_seconds": 1788
      },
      "Astronomy_002": {
        "score": 20,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Astronomy_002_20260414_224929",
        "cost_usd": 0.931125,
        "duration_seconds": 2483
      },
      "Astronomy_003": {
        "score": 46.9,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Astronomy_003_20260414_233052",
        "cost_usd": 0.148125,
        "duration_seconds": 395
      },
      "Chemistry_000": {
        "score": 17.9,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Chemistry_000_20260414_233727",
        "cost_usd": 3.007125,
        "duration_seconds": 8019
      },
      "Chemistry_001": {
        "score": 3.95,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Chemistry_001_20260415_015105",
        "cost_usd": 0.52725,
        "duration_seconds": 1406
      },
      "Chemistry_002": {
        "score": 0,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Chemistry_002_20260415_021431",
        "cost_usd": 0.145125,
        "duration_seconds": 387
      },
      "Chemistry_003": {
        "score": 9,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Chemistry_003_20260415_022059",
        "cost_usd": 0.582,
        "duration_seconds": 1552
      },
      "Earth_000": {
        "score": 14.2,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Earth_000_20260415_024651",
        "cost_usd": 0.13875,
        "duration_seconds": 370
      },
      "Earth_001": {
        "score": 26.63,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Earth_001_20260415_025301",
        "cost_usd": 0.172125,
        "duration_seconds": 459
      },
      "Earth_002": {
        "score": 24.4,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Earth_002_20260415_030040",
        "cost_usd": 0.310125,
        "duration_seconds": 827
      },
      "Earth_003": {
        "score": 1.2,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Earth_003_20260415_031428",
        "cost_usd": 0.398625,
        "duration_seconds": 1063
      },
      "Energy_000": {
        "score": 22,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Energy_000_20260415_130453",
        "cost_usd": 0.605625,
        "duration_seconds": 1615
      },
      "Energy_001": {
        "score": 24.7,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Energy_001_20260415_034329",
        "cost_usd": 0.426,
        "duration_seconds": 1136
      },
      "Energy_002": {
        "score": 30.55,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Energy_002_20260415_040225",
        "cost_usd": 0.1755,
        "duration_seconds": 468
      },
      "Energy_003": {
        "score": 7.5,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Energy_003_20260415_133148",
        "cost_usd": 0.3765,
        "duration_seconds": 1004
      },
      "Information_000": {
        "score": 47.1,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Information_000_20260415_134832",
        "cost_usd": 1.26375,
        "duration_seconds": 3370
      },
      "Information_001": {
        "score": 5.6,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Information_001_20260415_144442",
        "cost_usd": 0.270375,
        "duration_seconds": 721
      },
      "Information_002": {
        "score": 12,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Information_002_20260415_145643",
        "cost_usd": 0.1725,
        "duration_seconds": 460
      },
      "Information_003": {
        "score": 5.95,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Information_003_20260415_171427",
        "cost_usd": 0.496875,
        "duration_seconds": 1325
      },
      "Life_000": {
        "score": 7,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Life_000_20260415_094527",
        "cost_usd": 0.891,
        "duration_seconds": 2376
      },
      "Life_001": {
        "score": 5.7,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Life_001_20260415_102503",
        "cost_usd": 0.159375,
        "duration_seconds": 425
      },
      "Life_002": {
        "score": 7.3,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Life_002_20260415_103208",
        "cost_usd": 0.238875,
        "duration_seconds": 637
      },
      "Life_003": {
        "score": 28.4,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Life_003_20260415_104245",
        "cost_usd": 0.138,
        "duration_seconds": 368
      },
      "Material_000": {
        "score": 20.8,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Material_000_20260415_104854",
        "cost_usd": 0.982125,
        "duration_seconds": 2619
      },
      "Material_001": {
        "score": 15.95,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Material_001_20260415_113232",
        "cost_usd": 0.324,
        "duration_seconds": 864
      },
      "Material_002": {
        "score": 27.05,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Material_002_20260415_114656",
        "cost_usd": 0.301875,
        "duration_seconds": 805
      },
      "Material_003": {
        "score": 14.45,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Material_003_20260415_120022",
        "cost_usd": 0.871125,
        "duration_seconds": 2323
      },
      "Math_000": {
        "score": 23.5,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Math_000_20260415_191952",
        "cost_usd": 0.684375,
        "duration_seconds": 1825
      },
      "Math_001": {
        "score": 33.1,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Math_001_20260415_131344",
        "cost_usd": 0.348,
        "duration_seconds": 928
      },
      "Math_002": {
        "score": 9.6,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Math_002_20260415_132912",
        "cost_usd": 1.197,
        "duration_seconds": 3192
      },
      "Math_003": {
        "score": 10,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Math_003_20260415_142226",
        "cost_usd": 0.550125,
        "duration_seconds": 1467
      },
      "Neuroscience_000": {
        "score": 8.6,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Neuroscience_000_20260415_101555",
        "cost_usd": 0.157875,
        "duration_seconds": 421
      },
      "Neuroscience_001": {
        "score": 2,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Neuroscience_001_20260415_102256",
        "cost_usd": 0.35325,
        "duration_seconds": 942
      },
      "Neuroscience_002": {
        "score": 0.75,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Neuroscience_002_20260415_103839",
        "cost_usd": 0.7005,
        "duration_seconds": 1868
      },
      "Neuroscience_003": {
        "score": 7.2,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Neuroscience_003_20260415_110948",
        "cost_usd": 0.4425,
        "duration_seconds": 1180
      },
      "Physics_000": {
        "score": 24.8,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Physics_000_20260415_164039",
        "cost_usd": 0.254625,
        "duration_seconds": 679
      },
      "Physics_001": {
        "score": 27.55,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Physics_001_20260415_113755",
        "cost_usd": 0.285375,
        "duration_seconds": 761
      },
      "Physics_002": {
        "score": 28.5,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Physics_002_20260415_115036",
        "cost_usd": 0.21225,
        "duration_seconds": 566
      },
      "Physics_003": {
        "score": 41.8,
        "model": "Qwen3.6-Plus",
        "model_display": "Qwen3.6-Plus",
        "run_id": "Physics_003_20260415_122845",
        "cost_usd": 0.20475,
        "duration_seconds": 546
      }
    },
    "ResearchHarness (Qwen3.7-Max)": {
      "Astronomy_000": {
        "score": 15.9,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Astronomy_000_20260527_123627",
        "cost_usd": 0.504375,
        "duration_seconds": 807
      },
      "Astronomy_001": {
        "score": 11,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Astronomy_001_20260526_201220",
        "cost_usd": 0.200625,
        "duration_seconds": 321
      },
      "Astronomy_002": {
        "score": 28,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Astronomy_002_20260526_201800",
        "cost_usd": 0.556875,
        "duration_seconds": 891
      },
      "Astronomy_003": {
        "score": 40.2,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Astronomy_003_20260526_203301",
        "cost_usd": 0.20625,
        "duration_seconds": 330
      },
      "Chemistry_000": {
        "score": 13.25,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Chemistry_000_20260526_203850",
        "cost_usd": 1.383125,
        "duration_seconds": 2213
      },
      "Chemistry_001": {
        "score": 0.5,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Chemistry_001_20260526_211600",
        "cost_usd": 0.43375,
        "duration_seconds": 694
      },
      "Chemistry_002": {
        "score": 1,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Chemistry_002_20260527_102132",
        "cost_usd": 0.349375,
        "duration_seconds": 559
      },
      "Chemistry_003": {
        "score": 12.9,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Chemistry_003_20260527_125008",
        "cost_usd": 0.53375,
        "duration_seconds": 854
      },
      "Earth_000": {
        "score": 12.5,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Earth_000_20260526_214031",
        "cost_usd": 0.211875,
        "duration_seconds": 339
      },
      "Earth_001": {
        "score": 36.65,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Earth_001_20260526_214648",
        "cost_usd": 0.22125,
        "duration_seconds": 354
      },
      "Earth_002": {
        "score": 9.6,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Earth_002_20260526_215300",
        "cost_usd": 0.35125,
        "duration_seconds": 562
      },
      "Earth_003": {
        "score": 0.6,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Earth_003_20260526_220242",
        "cost_usd": 0.355,
        "duration_seconds": 568
      },
      "Energy_001": {
        "score": 27,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Energy_001_20260526_222002",
        "cost_usd": 0.230625,
        "duration_seconds": 369
      },
      "Energy_002": {
        "score": 32.35,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Energy_002_20260526_222628",
        "cost_usd": 0.509375,
        "duration_seconds": 815
      },
      "Energy_003": {
        "score": 16.5,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Energy_003_20260527_104651",
        "cost_usd": 0.30375,
        "duration_seconds": 486
      },
      "Information_002": {
        "score": 38.4,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Information_002_20260526_225326",
        "cost_usd": 0.170625,
        "duration_seconds": 273
      },
      "Information_003": {
        "score": 5.25,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Information_003_20260526_225818",
        "cost_usd": 0.446875,
        "duration_seconds": 715
      },
      "Life_001": {
        "score": 0,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Life_001_20260526_231703",
        "cost_usd": 0.21375,
        "duration_seconds": 342
      },
      "Life_002": {
        "score": 6.1,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Life_002_20260526_232305",
        "cost_usd": 0.19125,
        "duration_seconds": 306
      },
      "Life_003": {
        "score": 24.8,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Life_003_20260526_232817",
        "cost_usd": 0.190625,
        "duration_seconds": 305
      },
      "Material_001": {
        "score": 15.9,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Material_001_20260527_111743",
        "cost_usd": 0.32,
        "duration_seconds": 512
      },
      "Material_002": {
        "score": 30.49,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Material_002_20260527_001300",
        "cost_usd": 0.89375,
        "duration_seconds": 1430
      },
      "Material_003": {
        "score": 25.25,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Material_003_20260527_145708",
        "cost_usd": 0.811875,
        "duration_seconds": 1299
      },
      "Math_000": {
        "score": 29.05,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Math_000_20260527_004252",
        "cost_usd": 0.2975,
        "duration_seconds": 476
      },
      "Math_001": {
        "score": 31.2,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Math_001_20260527_005133",
        "cost_usd": 0.295,
        "duration_seconds": 472
      },
      "Math_002": {
        "score": 19.1,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Math_002_20260527_005940",
        "cost_usd": 0.315625,
        "duration_seconds": 505
      },
      "Math_003": {
        "score": 10,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Math_003_20260527_133920",
        "cost_usd": 0.28125,
        "duration_seconds": 450
      },
      "Neuroscience_000": {
        "score": 11,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Neuroscience_000_20260527_011357",
        "cost_usd": 0.255625,
        "duration_seconds": 409
      },
      "Neuroscience_001": {
        "score": 3.75,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Neuroscience_001_20260527_012118",
        "cost_usd": 0.29375,
        "duration_seconds": 470
      },
      "Neuroscience_002": {
        "score": 0,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Neuroscience_002_20260527_013027",
        "cost_usd": 0.9675,
        "duration_seconds": 1548
      },
      "Neuroscience_003": {
        "score": 13.15,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Neuroscience_003_20260527_151915",
        "cost_usd": 1.20125,
        "duration_seconds": 1922
      },
      "Physics_001": {
        "score": 29.45,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Physics_001_20260527_021219",
        "cost_usd": 0.218125,
        "duration_seconds": 349
      },
      "Physics_002": {
        "score": 40.05,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Physics_002_20260527_021848",
        "cost_usd": 0.24375,
        "duration_seconds": 390
      },
      "Physics_003": {
        "score": 45.4,
        "model": "qwen3.7-max",
        "model_display": "Qwen3.7-Max",
        "run_id": "Physics_003_20260527_022559",
        "cost_usd": 0.2325,
        "duration_seconds": 372
      }
    }
  }
}
