{
  "schemaVersion": 2,
  "sourceUrl": "https://swescience.github.io/",
  "sourceRepository": "https://github.com/swescience/swescience.github.io",
  "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7",
  "sourceUpdatedAt": "2026-09-10",
  "inputs": [
    {
      "file": "benchmark.json",
      "url": "https://raw.githubusercontent.com/swescience/swescience.github.io/1855c66633613e53eff681a55dcf513461f7eca7/data/benchmark.json",
      "sha256": "3e2410026481af404c5058f95f195908747e6742f2da7141baa81d52f406a419"
    },
    {
      "file": "hard70-model-results.json",
      "url": "https://raw.githubusercontent.com/swescience/swescience.github.io/1855c66633613e53eff681a55dcf513461f7eca7/data/hard70-model-results.json",
      "sha256": "818339ff18728865c44e9da7e3d9d4fdb89581eef39414102fdef9969160be50"
    },
    {
      "file": "task-matrix.json",
      "url": "https://raw.githubusercontent.com/swescience/swescience.github.io/1855c66633613e53eff681a55dcf513461f7eca7/data/task-matrix.json",
      "sha256": "d278d86768fedf3b4d1ab4c7643b2349d7edd3a580d370050fd6d401c9dce708"
    }
  ],
  "benchmarkSummary": {
    "tasks": 119,
    "repositories": 98,
    "domains": 20
  },
  "subset": {
    "id": "biology-bme-v1",
    "name": "Biology & biomedical engineering",
    "sourceUrl": "https://arxiv.org/abs/2608.19799v2",
    "sourceTable": "Appendix B, Table 5; counts cross-checked against Appendix A, Table 4",
    "fullTaskCount": 119,
    "groups": {
      "Biology": [
        "004",
        "006",
        "016",
        "018",
        "019",
        "028",
        "029",
        "063",
        "068",
        "069",
        "070",
        "073",
        "081"
      ],
      "Biomedical Engineering": [
        "005",
        "007",
        "015",
        "022",
        "025",
        "031",
        "037",
        "053",
        "060",
        "072",
        "087",
        "093"
      ]
    }
  },
  "excludedModels": [
    {
      "sourceModelId": "deepseek-high",
      "modelFamily": "DeepSeek-V4-flash",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "qwen",
      "modelFamily": "Qwen3.5-397B",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "agents-a1",
      "modelFamily": "Agents-A1",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "bigbang-v1",
      "modelFamily": "BigBang-v1",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "qwen-3-5-9b",
      "modelFamily": "Qwen3.5-9B",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "qwen-3-6-35b-a3b",
      "modelFamily": "Qwen3.6-35B-A3B",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    },
    {
      "sourceModelId": "nex-n2-mini",
      "modelFamily": "Nex-N2-mini",
      "reason": "Incomplete published task-level coverage; not treated as zero",
      "availableTaskCount": 0
    }
  ],
  "taskOutcomes": [
    {
      "sourceModelId": "opus",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 1
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 1
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 1
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 1
        },
        {
          "taskId": "087",
          "reward": 1
        },
        {
          "taskId": "093",
          "reward": 1
        }
      ]
    },
    {
      "sourceModelId": "deepseek-pro",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 1
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 0
        },
        {
          "taskId": "063",
          "reward": 1
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 1
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 1
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "kimi",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 0
        },
        {
          "taskId": "063",
          "reward": 1
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 1
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "glm",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 0
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 1
        },
        {
          "taskId": "063",
          "reward": 1
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 0
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 0
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 1
        }
      ]
    },
    {
      "sourceModelId": "gpt",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 1
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 0
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "gpt-6-astra",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 1
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 1
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 1
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 1
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 0
        },
        {
          "taskId": "060",
          "reward": 1
        },
        {
          "taskId": "072",
          "reward": 1
        },
        {
          "taskId": "087",
          "reward": 1
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "nex",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 0
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 1
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 0
        },
        {
          "taskId": "022",
          "reward": 0
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "deepseek-max",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 0
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 0
        },
        {
          "taskId": "025",
          "reward": 0
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "qwen-3-8-27b",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 1
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 0
        },
        {
          "taskId": "063",
          "reward": 1
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 1
        },
        {
          "taskId": "015",
          "reward": 1
        },
        {
          "taskId": "022",
          "reward": 0
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 1
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    },
    {
      "sourceModelId": "intern-s2-preview-397b",
      "outcomes": [
        {
          "taskId": "004",
          "reward": 0
        },
        {
          "taskId": "006",
          "reward": 0
        },
        {
          "taskId": "016",
          "reward": 1
        },
        {
          "taskId": "018",
          "reward": 1
        },
        {
          "taskId": "019",
          "reward": 0
        },
        {
          "taskId": "028",
          "reward": 1
        },
        {
          "taskId": "029",
          "reward": 0
        },
        {
          "taskId": "063",
          "reward": 0
        },
        {
          "taskId": "068",
          "reward": 0
        },
        {
          "taskId": "069",
          "reward": 1
        },
        {
          "taskId": "070",
          "reward": 0
        },
        {
          "taskId": "073",
          "reward": 0
        },
        {
          "taskId": "081",
          "reward": 1
        },
        {
          "taskId": "005",
          "reward": 0
        },
        {
          "taskId": "007",
          "reward": 0
        },
        {
          "taskId": "015",
          "reward": 0
        },
        {
          "taskId": "022",
          "reward": 0
        },
        {
          "taskId": "025",
          "reward": 1
        },
        {
          "taskId": "031",
          "reward": 1
        },
        {
          "taskId": "037",
          "reward": 0
        },
        {
          "taskId": "053",
          "reward": 0
        },
        {
          "taskId": "060",
          "reward": 0
        },
        {
          "taskId": "072",
          "reward": 0
        },
        {
          "taskId": "087",
          "reward": 0
        },
        {
          "taskId": "093",
          "reward": 0
        }
      ]
    }
  ],
  "scoresBySlug": {
    "swe-bench-science": [
      {
        "resultId": "swe-bench-science:biology-bme-v1:opus",
        "sourceModelId": "opus",
        "model": "Claude-Opus-5 (max) · Claude Code",
        "modelFamily": "Claude-Opus-5",
        "harness": "Claude Code",
        "reasoningEffort": "max",
        "score": 0.68,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 17,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 8
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 9
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:deepseek-pro",
        "sourceModelId": "deepseek-pro",
        "model": "DeepSeek-V4-Pro (max) · Claude Code",
        "modelFamily": "DeepSeek-V4-Pro",
        "harness": "Claude Code",
        "reasoningEffort": "max",
        "score": 0.6,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 15,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 8
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 7
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:kimi",
        "sourceModelId": "kimi",
        "model": "Kimi-K3 (max) · Kimi Code",
        "modelFamily": "Kimi-K3",
        "harness": "Kimi Code",
        "reasoningEffort": "max",
        "score": 0.52,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 13,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 7
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 6
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:glm",
        "sourceModelId": "glm",
        "model": "GLM-5.2 (max) · Codex",
        "modelFamily": "GLM-5.2",
        "harness": "Codex",
        "reasoningEffort": "max",
        "score": 0.44,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 11,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 7
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 4
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:gpt",
        "sourceModelId": "gpt",
        "model": "GPT-5.6-sol (max) · Codex",
        "modelFamily": "GPT-5.6-sol",
        "harness": "Codex",
        "reasoningEffort": "max",
        "score": 0.44,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 11,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 7
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 4
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:gpt-6-astra",
        "sourceModelId": "gpt-6-astra",
        "model": "GPT-6 Astra (max) · Codex",
        "modelFamily": "GPT-6 Astra",
        "harness": "Codex",
        "reasoningEffort": "max",
        "score": 0.64,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 16,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 8
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 8
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:nex",
        "sourceModelId": "nex",
        "model": "Nex N2 (default) · Codex",
        "modelFamily": "Nex N2",
        "harness": "Codex",
        "reasoningEffort": "default",
        "score": 0.36,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 9,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 6
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 3
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:deepseek-max",
        "sourceModelId": "deepseek-max",
        "model": "DeepSeek-V4-flash (max) · Claude Code",
        "modelFamily": "DeepSeek-V4-flash",
        "harness": "Claude Code",
        "reasoningEffort": "max",
        "score": 0.36,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 9,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 6
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 3
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:qwen-3-8-27b",
        "sourceModelId": "qwen-3-8-27b",
        "model": "Qwen3.8-27B (xhigh) · Claude Code",
        "modelFamily": "Qwen3.8-27B",
        "harness": "Claude Code",
        "reasoningEffort": "xhigh",
        "score": 0.48,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 12,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 7
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 5
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      },
      {
        "resultId": "swe-bench-science:biology-bme-v1:intern-s2-preview-397b",
        "sourceModelId": "intern-s2-preview-397b",
        "model": "Intern-S2-Preview-397B (max) · Claude Code",
        "modelFamily": "Intern-S2-Preview-397B",
        "harness": "Claude Code",
        "reasoningEffort": "max",
        "score": 0.28,
        "metric": "Pass@1",
        "variant": "Biology + BME · 25 tasks",
        "sampleCount": 25,
        "passedCount": 7,
        "domainResults": [
          {
            "domain": "Biology",
            "sampleCount": 13,
            "passedCount": 5
          },
          {
            "domain": "Biomedical Engineering",
            "sampleCount": 12,
            "passedCount": 2
          }
        ],
        "derivation": "BioInspect-calculated subset of official published binary task outcomes; not a BioInspect execution",
        "date": "2026-09-10",
        "dateMeaning": "leaderboard update date, not execution date",
        "sourceType": "official-leaderboard",
        "sourceUrl": "https://swescience.github.io/",
        "sourceTitle": "Official task outcomes · BioInspect subset calculation",
        "verifiedBy": "external",
        "sourceRevision": "1855c66633613e53eff681a55dcf513461f7eca7"
      }
    ]
  }
}
