{
  "schemaVersion": 1,
  "resultVersion": "v1",
  "generatedBy": "scripts/build-v2-results.mjs",
  "generatedAt": "2026-10-13T15:43:09.595Z",
  "dataUpdatedAt": "2026-10-09",
  "provenance": {
    "description": "V2 score arrays in src/App.tsx, checked against the per-evaluation files in public/data/v1/. BioSecBench-Refusal scores come from public/data/v1/refusalbench.json. Overall weights come from public/data/aggregate-leaderboard.json. OncologyBench strict results use the selected 25 evaluations in the October 2 export, nine of them re-graded against a new decision rubric in the October 9 export, generated by scripts/build-oncologybench.mjs.",
    "sourcePaths": [
      "src/App.tsx",
      "public/data/v1/",
      "public/data/aggregate-leaderboard.json",
      "public/data/oncologybench/index.json",
      "scripts/oncologybench-src/"
    ]
  },
  "canonicalUrl": "https://benchmarks.bio/results/v1/",
  "methodology": "Overall Capabilities score is the weighted mean of each V1 benchmark's macro-mean pass rate. The weights are the configured evaluation counts in the aggregate leaderboard metadata; these can differ from the number of V1 evaluation records. Safeguards is the BioSecBench-Refusal score.",
  "defaultScope": {
    "assessment": "capabilities",
    "requiresCompleteCoverage": true
  },
  "benchmarks": [
    {
      "id": "spatialbench",
      "label": "SpatialBench",
      "category": "multiomics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 115,
      "overallWeightEvaluationCount": 115,
      "weight": 1
    },
    {
      "id": "spatialbench-long",
      "label": "SpatialBench-Long",
      "category": "multiomics",
      "horizon": "long",
      "assessment": "capabilities",
      "v2EvaluationCount": 21,
      "overallWeightEvaluationCount": 24,
      "weight": 1
    },
    {
      "id": "scbench",
      "label": "scBench",
      "category": "multiomics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 195,
      "overallWeightEvaluationCount": 195,
      "weight": 1
    },
    {
      "id": "scbench-long",
      "label": "scBench-Long",
      "category": "multiomics",
      "horizon": "long",
      "assessment": "capabilities",
      "v2EvaluationCount": 22,
      "overallWeightEvaluationCount": 21,
      "weight": 1
    },
    {
      "id": "epibench",
      "label": "EpiBench",
      "category": "multiomics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 106,
      "overallWeightEvaluationCount": 106,
      "weight": 1
    },
    {
      "id": "variantbench",
      "label": "VariantBench",
      "category": "multiomics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 118,
      "overallWeightEvaluationCount": 118,
      "weight": 1
    },
    {
      "id": "metagenomics",
      "label": "MetagenomicsBench",
      "category": "multiomics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 100,
      "overallWeightEvaluationCount": 100,
      "weight": 1
    },
    {
      "id": "txbench-ab",
      "label": "TxBench-Antibody-Discovery",
      "category": "therapeutics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 100,
      "overallWeightEvaluationCount": 100,
      "weight": 1
    },
    {
      "id": "txbench-pp",
      "label": "TxBench-Preclinical-Pharmacology",
      "category": "therapeutics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 100,
      "overallWeightEvaluationCount": 100,
      "weight": 1
    },
    {
      "id": "txbench-od",
      "label": "TxBench-Oligo-Discovery",
      "category": "therapeutics",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 113,
      "overallWeightEvaluationCount": 113,
      "weight": 1
    },
    {
      "id": "biosecbench-surveillance",
      "label": "BioSecBench-Surveillance",
      "category": "biosecurity",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 102,
      "overallWeightEvaluationCount": 102,
      "weight": 1
    },
    {
      "id": "biosecbench-refusal",
      "label": "BioSecBench-Refusal",
      "category": "biosecurity",
      "horizon": "short",
      "assessment": "safeguards",
      "v2EvaluationCount": 107,
      "overallWeightEvaluationCount": 107,
      "weight": 1
    },
    {
      "id": "functionbench",
      "label": "BioSecBench-Function",
      "category": "biosecurity",
      "horizon": "short",
      "assessment": "capabilities",
      "v2EvaluationCount": 111,
      "overallWeightEvaluationCount": 111,
      "weight": 1
    },
    {
      "id": "oncologybench",
      "label": "OncologyBench",
      "category": "applications",
      "horizon": "long",
      "assessment": "capabilities",
      "v2EvaluationCount": 25,
      "overallWeightEvaluationCount": 25,
      "weight": 1
    }
  ],
  "capabilitiesLeaderboard": [
    {
      "rank": 1,
      "id": "opus-5-5-lsvp-pi",
      "model": "Claude Opus 5.5*",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "spatialbench": 68.99,
        "spatialbench-long": 39.29,
        "scbench": 61.88,
        "scbench-long": 36.93,
        "epibench": 37.42,
        "variantbench": 48.59,
        "metagenomics": 62.33,
        "txbench-ab": 66.67,
        "txbench-pp": 65.33,
        "txbench-od": 59.88,
        "biosecbench-surveillance": 60.78,
        "functionbench": 56.06
      },
      "overallScorePct": 58.12509543568465,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 2,
      "id": "opus-5-5-lsvp-claude-code",
      "model": "Claude Opus 5.5*",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "spatialbench": 68.7,
        "spatialbench-long": 40.48,
        "scbench": 61.54,
        "scbench-long": 32.39,
        "epibench": 39.62,
        "variantbench": 48.87,
        "metagenomics": 62.67,
        "txbench-ab": 67.67,
        "txbench-pp": 65,
        "txbench-od": 62.24,
        "biosecbench-surveillance": 57.84,
        "functionbench": 54.24
      },
      "overallScorePct": 58.09653941908714,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 3,
      "id": "sonnet-5-5-pi",
      "model": "Claude Sonnet 5.5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 29.3333333333,
        "spatialbench": 72.75,
        "spatialbench-long": 34.92,
        "scbench": 60.34,
        "scbench-long": 30.3,
        "epibench": 30.19,
        "variantbench": 51.69,
        "metagenomics": 60,
        "txbench-ab": 54.67,
        "txbench-pp": 64.33,
        "txbench-od": 51.92,
        "functionbench": 51.71
      },
      "overallScorePct": 54.20797281323803,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "biosecbench-surveillance"
      ]
    },
    {
      "rank": 4,
      "id": "sonnet-5-5-claude-code",
      "model": "Claude Sonnet 5.5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 32,
        "spatialbench": 70.14,
        "spatialbench-long": 36.51,
        "scbench": 59.15,
        "scbench-long": 31.82,
        "epibench": 28.93,
        "variantbench": 51.13,
        "metagenomics": 60,
        "txbench-ab": 57.33,
        "txbench-pp": 62.33,
        "txbench-od": 51.92,
        "functionbench": 53.46
      },
      "overallScorePct": 53.911125886524815,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "biosecbench-surveillance"
      ]
    },
    {
      "rank": 5,
      "id": "fable-5-1-lsvp-claude-code",
      "model": "Claude Fable 5.1*",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "spatialbench": 67.54,
        "spatialbench-long": 29.76,
        "scbench": 60.51,
        "scbench-long": 25.57,
        "epibench": 31.76,
        "variantbench": 40.68,
        "metagenomics": 61.67,
        "txbench-ab": 63.33,
        "txbench-pp": 59.67,
        "txbench-od": 54.87,
        "biosecbench-surveillance": 49.02,
        "functionbench": 48.95
      },
      "overallScorePct": 53.18287136929461,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 6,
      "id": "gpt-6-1-sol-pi",
      "model": "GPT-6.1 Sol",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "spatialbench": 67.25,
        "spatialbench-long": 38.69,
        "scbench": 62.91,
        "scbench-long": 26.7,
        "epibench": 28.3,
        "variantbench": 46.05,
        "txbench-ab": 49.67,
        "txbench-pp": 59.67,
        "txbench-od": 52.51,
        "biosecbench-surveillance": 50.79,
        "functionbench": 46.03
      },
      "overallScorePct": 51.65764705882353,
      "benchmarkCoverage": "11/13",
      "missingBenchmarks": [
        "metagenomics",
        "oncologybench"
      ]
    },
    {
      "rank": 7,
      "id": "gpt-6-astra-pi",
      "model": "GPT-6 Astra",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 21.3333333333,
        "spatialbench": 66.67,
        "spatialbench-long": 37.5,
        "scbench": 63.93,
        "scbench-long": 27.27,
        "epibench": 28.3,
        "variantbench": 46.61,
        "metagenomics": 47,
        "txbench-ab": 56,
        "txbench-pp": 59.33,
        "txbench-od": 51.92,
        "biosecbench-surveillance": 48.52,
        "functionbench": 48.63,
        "biosecbench-refusal": 40.8
      },
      "overallScorePct": 51.28952303522967,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 8,
      "id": "opus-5-pi",
      "model": "Claude Opus 5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 40,
        "spatialbench": 68.41,
        "spatialbench-long": 27.98,
        "scbench": 58.29,
        "scbench-long": 27.27,
        "epibench": 25.16,
        "variantbench": 50.56,
        "metagenomics": 54,
        "txbench-ab": 48.67,
        "txbench-pp": 63,
        "txbench-od": 42.48,
        "biosecbench-surveillance": 51.48,
        "functionbench": 42.46,
        "biosecbench-refusal": 24.5
      },
      "overallScorePct": 49.952999999999996,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 9,
      "id": "gpt-6-1-sol-codex",
      "model": "GPT-6.1 Sol",
      "harness": "Codex",
      "provider": "OpenAI",
      "scores": {
        "spatialbench": 66.96,
        "spatialbench-long": 39.88,
        "scbench": 63.59,
        "scbench-long": 25,
        "epibench": 24.84,
        "variantbench": 43.22,
        "txbench-ab": 45.67,
        "txbench-pp": 55,
        "txbench-od": 49.56,
        "biosecbench-surveillance": 49.4,
        "functionbench": 44.58
      },
      "overallScorePct": 49.74663348416289,
      "benchmarkCoverage": "11/13",
      "missingBenchmarks": [
        "metagenomics",
        "oncologybench"
      ]
    },
    {
      "rank": 10,
      "id": "opus-5-claude-code",
      "model": "Claude Opus 5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 36,
        "spatialbench": 68.41,
        "spatialbench-long": 30.95,
        "scbench": 57.61,
        "scbench-long": 24.43,
        "epibench": 20.75,
        "variantbench": 52.82,
        "metagenomics": 53.33,
        "txbench-ab": 48,
        "txbench-pp": 59.67,
        "txbench-od": 48.38,
        "biosecbench-surveillance": 43.59,
        "functionbench": 44.75,
        "biosecbench-refusal": 31.8
      },
      "overallScorePct": 49.32484552845529,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 11,
      "id": "gpt-6-astra-codex",
      "model": "GPT-6 Astra",
      "harness": "Codex",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 18.6666666667,
        "spatialbench": 67.54,
        "spatialbench-long": 39.29,
        "scbench": 63.42,
        "scbench-long": 25,
        "epibench": 24.21,
        "variantbench": 45.2,
        "metagenomics": 49.67,
        "txbench-ab": 52.67,
        "txbench-pp": 59.33,
        "txbench-od": 50.74,
        "biosecbench-surveillance": 35.19,
        "functionbench": 46.02,
        "biosecbench-refusal": 25.5
      },
      "overallScorePct": 49.24122493225,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 12,
      "id": "grok-4-6-pi",
      "model": "Grok 4.6",
      "harness": "Pi",
      "provider": "SpaceXAI",
      "scores": {
        "oncologybench": 18.6666666667,
        "spatialbench": 67.25,
        "spatialbench-long": 26.19,
        "scbench": 59.15,
        "scbench-long": 16.48,
        "epibench": 23.58,
        "variantbench": 40.4,
        "metagenomics": 38.67,
        "txbench-ab": 53,
        "txbench-pp": 61.67,
        "txbench-od": 46.02,
        "biosecbench-surveillance": 47.52,
        "functionbench": 44.04,
        "biosecbench-refusal": 46.9
      },
      "overallScorePct": 47.35424932249391,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 13,
      "id": "grok-4-7-grok-build",
      "model": "Grok 4.7",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scores": {
        "oncologybench": 18.6666666667,
        "spatialbench": 69.57,
        "spatialbench-long": 24.4,
        "scbench": 58.46,
        "scbench-long": 11.36,
        "epibench": 20.75,
        "variantbench": 45.48,
        "metagenomics": 48.67,
        "txbench-ab": 52,
        "txbench-pp": 54.67,
        "txbench-od": 41.89,
        "biosecbench-surveillance": 48.04,
        "functionbench": 43.33,
        "biosecbench-refusal": 62.4
      },
      "overallScorePct": 47.34511924119309,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 14,
      "id": "gpt-6-sol-pi",
      "model": "GPT-6 Sol",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 18.6666666667,
        "spatialbench": 67.54,
        "spatialbench-long": 31.55,
        "scbench": 61.54,
        "scbench-long": 28.41,
        "epibench": 22.01,
        "variantbench": 38.7,
        "metagenomics": 42,
        "txbench-ab": 43.33,
        "txbench-pp": 63,
        "txbench-od": 43.07,
        "biosecbench-surveillance": 47.74,
        "functionbench": 39.27
      },
      "overallScorePct": 46.67959078590854,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 15,
      "id": "grok-4-6-grok-build",
      "model": "Grok 4.6",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scores": {
        "oncologybench": 17.3333333333,
        "spatialbench": 66.09,
        "spatialbench-long": 27.38,
        "scbench": 57.61,
        "scbench-long": 15.91,
        "epibench": 21.07,
        "variantbench": 38.98,
        "metagenomics": 42,
        "txbench-ab": 51.67,
        "txbench-pp": 57,
        "txbench-od": 44.25,
        "biosecbench-surveillance": 48.04,
        "functionbench": 39.94,
        "biosecbench-refusal": 45.6
      },
      "overallScorePct": 45.928937669376026,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 16,
      "id": "opus-4-8-pi",
      "model": "Claude Opus 4.8",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 16,
        "spatialbench": 65.8,
        "spatialbench-long": 33.33,
        "scbench": 57.09,
        "scbench-long": 16.48,
        "epibench": 25.79,
        "variantbench": 42.37,
        "metagenomics": 48.33,
        "txbench-ab": 33.33,
        "txbench-pp": 57.67,
        "txbench-od": 37.46,
        "biosecbench-surveillance": 46.89,
        "functionbench": 43.07
      },
      "overallScorePct": 45.29144715447154,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 17,
      "id": "opus-4-8-claude-code",
      "model": "Claude Opus 4.8",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 16,
        "spatialbench": 66.96,
        "spatialbench-long": 27.38,
        "scbench": 56.24,
        "scbench-long": 21.02,
        "epibench": 20.44,
        "variantbench": 42.37,
        "metagenomics": 50,
        "txbench-ab": 35.33,
        "txbench-pp": 54.33,
        "txbench-od": 35.99,
        "biosecbench-surveillance": 37.34,
        "functionbench": 38.97
      },
      "overallScorePct": 43.49533333333333,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 18,
      "id": "gpt-5-6-sol-pi",
      "model": "GPT-5.6 Sol",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 18.6666666667,
        "spatialbench": 67.54,
        "spatialbench-long": 37.5,
        "scbench": 58.8,
        "scbench-long": 27.84,
        "epibench": 21.38,
        "variantbench": 35.31,
        "metagenomics": 31.33,
        "txbench-ab": 37.33,
        "txbench-pp": 61.33,
        "txbench-od": 35.99,
        "biosecbench-surveillance": 47.07,
        "functionbench": 34.36
      },
      "overallScorePct": 43.33189972899797,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 19,
      "id": "opus-5-5-pi",
      "model": "Claude Opus 5.5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 29.3333333333,
        "spatialbench": 72.75,
        "spatialbench-long": 20.24,
        "scbench": 55.38,
        "scbench-long": 6.82,
        "epibench": 38.99,
        "variantbench": 50.56,
        "metagenomics": 39.33,
        "txbench-ab": 8.33,
        "txbench-pp": 26.33,
        "txbench-od": 1.47,
        "biosecbench-surveillance": 55.81,
        "functionbench": 73.61
      },
      "overallScorePct": 42.32123848238415,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 20,
      "id": "deepseek-v4-1-flash-pi",
      "model": "DeepSeek V4.1 Flash",
      "harness": "Pi",
      "provider": "DeepSeek",
      "scores": {
        "oncologybench": 14.6666666667,
        "spatialbench": 63.19,
        "spatialbench-long": 26.19,
        "scbench": 54.7,
        "scbench-long": 14.77,
        "epibench": 25.47,
        "variantbench": 31.07,
        "metagenomics": 38,
        "txbench-pp": 46.67,
        "txbench-od": 34.81,
        "biosecbench-surveillance": 51.47,
        "functionbench": 40.84
      },
      "overallScorePct": 42.290740412980085,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "txbench-ab"
      ]
    },
    {
      "rank": 21,
      "id": "gpt-5-6-sol-codex",
      "model": "GPT-5.6 Sol",
      "harness": "Codex",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 14.6666666667,
        "spatialbench": 68.12,
        "spatialbench-long": 36.31,
        "scbench": 59.83,
        "scbench-long": 29.55,
        "epibench": 25.79,
        "variantbench": 34.18,
        "metagenomics": 28.67,
        "txbench-ab": 37,
        "txbench-od": 37.17,
        "biosecbench-surveillance": 47.26,
        "functionbench": 35.52
      },
      "overallScorePct": 42.17410324483849,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "txbench-pp"
      ]
    },
    {
      "rank": 22,
      "id": "opus-5-5-claude-code",
      "model": "Claude Opus 5.5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 37.3333333333,
        "spatialbench": 69.57,
        "spatialbench-long": 19.64,
        "scbench": 56.41,
        "scbench-long": 13.64,
        "epibench": 38.68,
        "variantbench": 49.72,
        "metagenomics": 43.67,
        "txbench-ab": 8,
        "txbench-pp": 30.67,
        "txbench-od": 1.18,
        "biosecbench-surveillance": 58.53,
        "functionbench": 61.54
      },
      "overallScorePct": 42.135783197831294,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 23,
      "id": "gpt-5-5-pi",
      "model": "GPT-5.5",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 14.6666666667,
        "spatialbench": 64.06,
        "spatialbench-long": 32.14,
        "scbench": 57.09,
        "scbench-long": 21.59,
        "epibench": 28.3,
        "variantbench": 30.51,
        "txbench-ab": 33,
        "txbench-pp": 55.33,
        "txbench-od": 33.92,
        "biosecbench-surveillance": 47.08,
        "functionbench": 28.31
      },
      "overallScorePct": 41.85962536873231,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "metagenomics"
      ]
    },
    {
      "rank": 24,
      "id": "sonnet-5-pi",
      "model": "Claude Sonnet 5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 14.6666666667,
        "spatialbench": 66.67,
        "spatialbench-long": 24.4,
        "scbench": 55.56,
        "scbench-long": 15.91,
        "epibench": 19.5,
        "variantbench": 39.83,
        "metagenomics": 42.33,
        "txbench-ab": 27.67,
        "txbench-pp": 49.33,
        "txbench-od": 36.58,
        "biosecbench-surveillance": 39.05,
        "functionbench": 33.11
      },
      "overallScorePct": 40.87757452574593,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 25,
      "id": "gemini-3-7-flash-pi",
      "model": "Gemini 3.7 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scores": {
        "oncologybench": 14.6666666667,
        "spatialbench": 59.13,
        "spatialbench-long": 29.76,
        "scbench": 50.43,
        "scbench-long": 18.75,
        "epibench": 22.01,
        "variantbench": 31.36,
        "metagenomics": 31.67,
        "txbench-ab": 50.67,
        "txbench-pp": 55.33,
        "txbench-od": 37.76,
        "biosecbench-surveillance": 41.46,
        "functionbench": 33.66,
        "biosecbench-refusal": 54.8
      },
      "overallScorePct": 40.765086720867885,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 26,
      "id": "sonnet-5-claude-code",
      "model": "Claude Sonnet 5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 12,
        "spatialbench": 65.8,
        "spatialbench-long": 20.24,
        "scbench": 53.85,
        "scbench-long": 15.91,
        "epibench": 21.7,
        "variantbench": 38.98,
        "metagenomics": 41,
        "txbench-ab": 32,
        "txbench-pp": 49.33,
        "txbench-od": 33.92,
        "biosecbench-surveillance": 30.18,
        "functionbench": 33.78
      },
      "overallScorePct": 39.822243902439034,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 27,
      "id": "opus-4-7-pi",
      "model": "Claude Opus 4.7",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "spatialbench": 54.78,
        "spatialbench-long": 26.19,
        "scbench": 50.77,
        "scbench-long": 11.36,
        "epibench": 22.64,
        "variantbench": 35.03,
        "metagenomics": 35.33,
        "txbench-ab": 31.67,
        "txbench-pp": 45.33,
        "txbench-od": 31.86,
        "biosecbench-surveillance": 45.79,
        "functionbench": 30.75
      },
      "overallScorePct": 38.60361825726142,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 28,
      "id": "opus-4-7-claude-code",
      "model": "Claude Opus 4.7",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "spatialbench": 56.52,
        "spatialbench-long": 29.76,
        "scbench": 52.48,
        "scbench-long": 11.36,
        "epibench": 18.87,
        "variantbench": 33.05,
        "txbench-ab": 36,
        "txbench-pp": 42.33,
        "txbench-od": 31.27,
        "biosecbench-surveillance": 41.94,
        "functionbench": 30.25
      },
      "overallScorePct": 38.541592760181,
      "benchmarkCoverage": "11/13",
      "missingBenchmarks": [
        "metagenomics",
        "oncologybench"
      ]
    },
    {
      "rank": 29,
      "id": "gemini-3-8-flash-pi",
      "model": "Gemini 3.8 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scores": {
        "oncologybench": 13.3333333333,
        "spatialbench": 59.42,
        "spatialbench-long": 28.57,
        "scbench": 34.02,
        "scbench-long": 19.89,
        "epibench": 21.38,
        "variantbench": 31.36,
        "metagenomics": 26.67,
        "txbench-ab": 49,
        "txbench-pp": 54.67,
        "txbench-od": 35.1,
        "biosecbench-surveillance": 44.11,
        "functionbench": 35.96,
        "biosecbench-refusal": 47.4
      },
      "overallScorePct": 37.692474254741875,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 30,
      "id": "gpt-6-luna-pi",
      "model": "GPT-6 Luna",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 12,
        "spatialbench": 59.71,
        "spatialbench-long": 23.21,
        "scbench": 53.85,
        "scbench-long": 10.8,
        "epibench": 19.18,
        "variantbench": 27.68,
        "metagenomics": 30.67,
        "txbench-ab": 34,
        "txbench-pp": 44.33,
        "txbench-od": 33.63,
        "biosecbench-surveillance": 41.46,
        "functionbench": 27.25
      },
      "overallScorePct": 37.158065040650406,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 31,
      "id": "kimi-k3-pi",
      "model": "Kimi K3",
      "harness": "Pi",
      "provider": "Moonshot",
      "scores": {
        "oncologybench": 24,
        "spatialbench": 63.48,
        "spatialbench-long": 22.62,
        "scbench": 47.52,
        "scbench-long": 14.2,
        "epibench": 15.72,
        "variantbench": 31.36,
        "metagenomics": 27.33,
        "txbench-ab": 35.33,
        "txbench-pp": 39.67,
        "txbench-od": 31.27,
        "biosecbench-surveillance": 38.56,
        "functionbench": 32.73
      },
      "overallScorePct": 36.347268292682934,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 32,
      "id": "gpt-5-6-luna-codex",
      "model": "GPT-5.6 Luna",
      "harness": "Codex",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 10.6666666667,
        "spatialbench": 58.55,
        "spatialbench-long": 25,
        "scbench": 48.89,
        "scbench-long": 9.66,
        "epibench": 19.81,
        "variantbench": 27.12,
        "metagenomics": 24.33,
        "txbench-ab": 18.67,
        "txbench-pp": 43.67,
        "txbench-od": 23.01,
        "biosecbench-surveillance": 43.2,
        "functionbench": 26.25
      },
      "overallScorePct": 33.51514363143699,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 33,
      "id": "gpt-5-6-luna-pi",
      "model": "GPT-5.6 Luna",
      "harness": "Pi",
      "provider": "OpenAI",
      "scores": {
        "oncologybench": 10.6666666667,
        "spatialbench": 60.87,
        "spatialbench-long": 22.62,
        "scbench": 50.26,
        "scbench-long": 13.07,
        "epibench": 18.87,
        "variantbench": 24.01,
        "metagenomics": 22.67,
        "txbench-ab": 19.33,
        "txbench-pp": 43.33,
        "txbench-od": 23.01,
        "biosecbench-surveillance": 35.09,
        "functionbench": 27.59
      },
      "overallScorePct": 32.921111111111784,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 34,
      "id": "sonnet-4-6-pi",
      "model": "Claude Sonnet 4.6",
      "harness": "Pi",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 2.6666666667,
        "spatialbench": 53.91,
        "spatialbench-long": 22.62,
        "scbench": 39.49,
        "scbench-long": 8.52,
        "epibench": 18.87,
        "variantbench": 31.07,
        "metagenomics": 27.67,
        "txbench-ab": 26.33,
        "txbench-pp": 34.33,
        "txbench-od": 30.09,
        "biosecbench-surveillance": 32.34,
        "functionbench": 25.54
      },
      "overallScorePct": 31.481249322493905,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 35,
      "id": "sonnet-4-6-claude-code",
      "model": "Claude Sonnet 4.6",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scores": {
        "oncologybench": 5.3333333333,
        "spatialbench": 53.33,
        "spatialbench-long": 17.26,
        "scbench": 41.71,
        "scbench-long": 10.23,
        "epibench": 17.3,
        "variantbench": 26.27,
        "metagenomics": 28.33,
        "txbench-ab": 24.33,
        "txbench-pp": 33.33,
        "txbench-od": 28.02,
        "biosecbench-surveillance": 34.47,
        "functionbench": 27.34
      },
      "overallScorePct": 31.120653116530487,
      "benchmarkCoverage": "13/13",
      "missingBenchmarks": []
    },
    {
      "rank": 36,
      "id": "mistral-large-4-0-pi",
      "model": "Mistral Large 4.0 Preview",
      "harness": "Pi",
      "provider": "Mistral",
      "scores": {
        "spatialbench": 51.88,
        "spatialbench-long": 12.5,
        "scbench": 31.28,
        "scbench-long": 3.41,
        "epibench": 15.09,
        "variantbench": 22.03,
        "metagenomics": 20,
        "txbench-ab": 21.33,
        "txbench-pp": 29.67,
        "txbench-od": 24.19,
        "biosecbench-surveillance": 21.24,
        "functionbench": 25.23
      },
      "overallScorePct": 26.088771784232367,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 37,
      "id": "nemotron-3-ultra-550b-a55b-pi",
      "model": "Nemotron 3 Ultra 550B A55B",
      "harness": "Pi",
      "provider": "NVIDIA",
      "scores": {
        "spatialbench": 46.96,
        "spatialbench-long": 15.87,
        "scbench": 36.58,
        "scbench-long": 3.03,
        "epibench": 11.32,
        "variantbench": 17.8,
        "metagenomics": 16.33,
        "txbench-ab": 21,
        "txbench-pp": 22.67,
        "txbench-od": 25.07,
        "biosecbench-surveillance": 21.24,
        "functionbench": 21.62
      },
      "overallScorePct": 24.628663900414935,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    },
    {
      "rank": 38,
      "id": "nemotron-3-5-lightning-pi",
      "model": "Nemotron 3.5 Lightning",
      "harness": "Pi",
      "provider": "NVIDIA",
      "scores": {
        "spatialbench": 28.99,
        "spatialbench-long": 4.76,
        "scbench": 22.91,
        "scbench-long": 0,
        "epibench": 6.92,
        "variantbench": 14.41,
        "metagenomics": 7.67,
        "txbench-ab": 16,
        "txbench-pp": 10.33,
        "txbench-od": 8.55,
        "biosecbench-surveillance": 14.05,
        "functionbench": 13.81
      },
      "overallScorePct": 14.673526970954356,
      "benchmarkCoverage": "12/13",
      "missingBenchmarks": [
        "oncologybench"
      ]
    }
  ],
  "safeguardsLeaderboard": [
    {
      "rank": 1,
      "id": "grok-4-7-grok-build",
      "model": "Grok 4.7",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scorePct": 62.4
    },
    {
      "rank": 2,
      "id": "gemini-3-7-flash-pi",
      "model": "Gemini 3.7 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scorePct": 54.8
    },
    {
      "rank": 3,
      "id": "gemini-3-8-flash-pi",
      "model": "Gemini 3.8 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scorePct": 47.4
    },
    {
      "rank": 4,
      "id": "grok-4-6-pi",
      "model": "Grok 4.6",
      "harness": "Pi",
      "provider": "SpaceXAI",
      "scorePct": 46.9
    },
    {
      "rank": 5,
      "id": "grok-4-6-grok-build",
      "model": "Grok 4.6",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scorePct": 45.6
    },
    {
      "rank": 6,
      "id": "gpt-6-astra-pi",
      "model": "GPT-6 Astra",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 40.8
    },
    {
      "rank": 7,
      "id": "opus-5-claude-code",
      "model": "Claude Opus 5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 31.8
    },
    {
      "rank": 8,
      "id": "gpt-6-astra-codex",
      "model": "GPT-6 Astra",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 25.5
    },
    {
      "rank": 9,
      "id": "opus-5-pi",
      "model": "Claude Opus 5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 24.5
    }
  ]
}