{
  "schemaVersion": 1,
  "resultVersion": "v1",
  "generatedBy": "scripts/build-backrooms-results-table.mjs",
  "generatedAt": "2026-10-13T15:43:09.595Z",
  "dataUpdatedAt": "2026-10-09",
  "canonicalUrl": "https://benchmarks.bio/oncology",
  "artifactUrl": "https://benchmarks.bio/benchmarks/oncologybench/",
  "benchmark": {
    "id": "oncologybench",
    "label": "OncologyBench",
    "category": "applications",
    "horizon": "long",
    "evalCount": 25,
    "scoreScope": {
      "label": "Selected release (strict task and decision pass)",
      "evaluationCount": 25
    },
    "weight": 1,
    "description": "OncologyBench tests whether AI agents can translate cancer research into real-world decisions about detection, diagnosis, treatment, and research priorities. Separate agents complete analytical tasks, and a final agent synthesizes their findings into a decision. Strict scores require full marks on both tasks and decisions across the selected 25 evaluations; refusals and timed-out slots remain in the denominator.",
    "repository": null,
    "paper": null,
    "paperPdfUrl": null,
    "interactiveUrl": "https://benchmarks.bio/oncology"
  },
  "scoreDefinition": "Published benchmark score on a 0–100 percentage scale using Selected release (strict task and decision pass) (25 evaluations); see the repository and paper for benchmark-specific grading methodology.",
  "results": [
    {
      "rank": 1,
      "id": "claude-opus-5-pi",
      "model": "Claude Opus 5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 40
    },
    {
      "rank": 2,
      "id": "opus-5-5-claude-code",
      "model": "Claude Opus 5.5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 37.3333333333
    },
    {
      "rank": 3,
      "id": "claude-opus-5-claude-code",
      "model": "Claude Opus 5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 36
    },
    {
      "rank": 4,
      "id": "sonnet-5-5-claude-code",
      "model": "Claude Sonnet 5.5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 32
    },
    {
      "rank": 5,
      "id": "sonnet-5-5-pi",
      "model": "Claude Sonnet 5.5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 29.3333333333
    },
    {
      "rank": 6,
      "id": "opus-5-5-pi",
      "model": "Claude Opus 5.5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 29.3333333333
    },
    {
      "rank": 7,
      "id": "kimi-k3-pi",
      "model": "Kimi K3",
      "harness": "Pi",
      "provider": "Moonshot",
      "scorePct": 24
    },
    {
      "rank": 8,
      "id": "gpt-6-astra-pi",
      "model": "GPT-6 Astra",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 21.3333333333
    },
    {
      "rank": 9,
      "id": "gpt-6-sol-codex",
      "model": "GPT-6 Sol",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 20
    },
    {
      "rank": 10,
      "id": "gpt-5-6-sol-pi",
      "model": "GPT-5.6 Sol",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 11,
      "id": "gpt-6-astra-codex",
      "model": "GPT-6 Astra",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 12,
      "id": "grok-4-6-pi",
      "model": "Grok 4.6",
      "harness": "Pi",
      "provider": "SpaceXAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 13,
      "id": "gpt-6-sol-pi",
      "model": "GPT-6 Sol",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 14,
      "id": "grok-4-7-grok-build",
      "model": "Grok 4.7",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 15,
      "id": "grok-4-7-pi",
      "model": "Grok 4.7",
      "harness": "Pi",
      "provider": "SpaceXAI",
      "scorePct": 18.6666666667
    },
    {
      "rank": 16,
      "id": "grok-4-6-grok-build",
      "model": "Grok 4.6",
      "harness": "Grok Build",
      "provider": "SpaceXAI",
      "scorePct": 17.3333333333
    },
    {
      "rank": 17,
      "id": "claude-opus-4-8-claude-code",
      "model": "Claude Opus 4.8",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 16
    },
    {
      "rank": 18,
      "id": "claude-opus-4-8-pi",
      "model": "Claude Opus 4.8",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 16
    },
    {
      "rank": 19,
      "id": "gpt-6-luna-codex",
      "model": "GPT-6 Luna",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 16
    },
    {
      "rank": 20,
      "id": "claude-sonnet-5-pi",
      "model": "Claude Sonnet 5",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 14.6666666667
    },
    {
      "rank": 21,
      "id": "deepseek-v4-1-flash-pi",
      "model": "DeepSeek V4.1 Flash",
      "harness": "Pi",
      "provider": "DeepSeek",
      "scorePct": 14.6666666667
    },
    {
      "rank": 22,
      "id": "gpt-5-5-pi",
      "model": "GPT-5.5",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 14.6666666667
    },
    {
      "rank": 23,
      "id": "gpt-5-6-sol-codex",
      "model": "GPT-5.6 Sol",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 14.6666666667
    },
    {
      "rank": 24,
      "id": "gemini-3-7-flash-pi",
      "model": "Gemini 3.7 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scorePct": 14.6666666667
    },
    {
      "rank": 25,
      "id": "gemini-3-8-flash-pi",
      "model": "Gemini 3.8 Flash",
      "harness": "Pi",
      "provider": "Google",
      "scorePct": 13.3333333333
    },
    {
      "rank": 26,
      "id": "claude-sonnet-5-claude-code",
      "model": "Claude Sonnet 5",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 12
    },
    {
      "rank": 27,
      "id": "gpt-6-luna-pi",
      "model": "GPT-6 Luna",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 12
    },
    {
      "rank": 28,
      "id": "gpt-5-6-luna-codex",
      "model": "GPT-5.6 Luna",
      "harness": "Codex",
      "provider": "OpenAI",
      "scorePct": 10.6666666667
    },
    {
      "rank": 29,
      "id": "gpt-5-6-luna-pi",
      "model": "GPT-5.6 Luna",
      "harness": "Pi",
      "provider": "OpenAI",
      "scorePct": 10.6666666667
    },
    {
      "rank": 30,
      "id": "sonnet-4-6-claude-code",
      "model": "Claude Sonnet 4.6",
      "harness": "Claude Code",
      "provider": "Anthropic",
      "scorePct": 5.3333333333
    },
    {
      "rank": 31,
      "id": "sonnet-4-6-pi",
      "model": "Claude Sonnet 4.6",
      "harness": "Pi",
      "provider": "Anthropic",
      "scorePct": 2.6666666667
    }
  ]
}
