{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "cmb",
  "name": "CMB (Chinese Medical Benchmark)",
  "summary": {
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。许可证宽松，但有来源风险：题目来自有版权的考试；只链接原出处。",
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. License is permissive, but source risk: questions come from copyrighted exams; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "benchmark-exam",
    "clinical-cases"
  ],
  "content_description": {
    "en": "Question bank and benchmark (multiple-choice questions plus clinical case consultations)",
    "zh": "题库与评测集（选择题+病案问诊）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "CMB-Exam 测试集11,200题、验证集280题、训练集269,359题；CMB-Clin 74例病案",
    "measures": [
      {
        "value": 11200,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "CMB-Exam test"
      },
      {
        "value": 280,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "CMB-Exam validation"
      },
      {
        "value": 269359,
        "unit": "questions",
        "qualifier": "exact",
        "scope": "CMB-Exam train"
      },
      {
        "value": 74,
        "unit": "cases",
        "qualifier": "exact",
        "scope": "CMB-Clin"
      }
    ]
  },
  "publisher": "FreedomIntelligence（深圳市大数据研究院支持）",
  "year": {
    "value": 2023,
    "raw": "2023"
  },
  "expert_review": {
    "en": "Three physicians took part in human evaluation of CMB-Clin; not stated for the rest",
    "zh": "CMB-Clin 由3名医生参与人工评测；其余未说明"
  },
  "license": {
    "legacy_status": "distributable",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "Repository and dataset card both state Apache-2.0",
      "zh": "仓库与数据集卡均为 Apache-2.0"
    },
    "evidence": [
      {
        "location": "repo-license",
        "location_detail": {
          "en": "GitHub repository license: Apache-2.0",
          "zh": "GitHub 仓库许可证：Apache-2.0"
        },
        "excerpt": "Apache License\nVersion 2.0, January 2004",
        "spdx": "Apache-2.0",
        "url": "https://github.com/FreedomIntelligence/CMB",
        "verified_on": "2026-11-12",
        "snapshot_id": "s04",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Hugging Face dataset card metadata: Apache-2.0",
          "zh": "Hugging Face 数据集卡元数据：Apache-2.0"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      },
      {
        "location": "readme",
        "location_detail": {
          "en": "README has no separate data license [Note: No license statement seen in snapshot s03, s04, s05]",
          "zh": "README 无单独数据许可［备注：快照中未见许可声明（快照 s03, s04, s05）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://github.com/FreedomIntelligence/CMB",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证宽松，但有来源风险：题目来自有版权的考试；只链接原出处。",
    "en": "License is permissive, but source risk: questions come from copyrighted exams; link only."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "Apache-2.0",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s04",
    "url": "https://github.com/FreedomIntelligence/CMB"
  },
  "risk_flags": [
    "exam-derived"
  ],
  "provenance": {
    "source_description": {
      "en": "The page does not state where the questions come from; the paper title describes a comprehensive Chinese medical benchmark",
      "zh": "页面未说明题目来源；论文标题为中文综合医学评测"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The page does not state the source of the exam questions",
      "zh": "页面未说明考试题来源"
    },
    {
      "en": "Sources include national medical licensing exam questions; in August 2026 the National Medical Examination Center issued a statement asserting copyright over past exam questions, so there is a source copyright risk",
      "zh": "来源含国家医学考试题，国家医学考试中心2026年8月声明主张历年试题著作权，存在来源版权风险"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/FreedomIntelligence/CMB",
      "https://huggingface.co/datasets/FreedomIntelligence/CMB"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "choice-question",
      "basis": "author-stated",
      "excerpt": "- question_type: *multiple-choice (单项选择题)* or *multiple-answer (多项选择题)*",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "multi-answer",
      "basis": "author-stated",
      "excerpt": "- question_type: *multiple-choice (单项选择题)* or *multiple-answer (多项选择题)*",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "CMB-Clin case QA.",
        "zh": "CMB-Clin 病案问答"
      },
      "scope": {
        "en": "CMB-Clin",
        "zh": "CMB-Clin"
      }
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "Please use the following citation if you intend to use our dataset for training or evaluation:",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "Please use the following citation if you intend to use our dataset for training or evaluation:",
      "snapshot_id": "s01"
    },
    {
      "facet": "annotation_depth",
      "value": "with-explanation",
      "basis": "author-stated",
      "excerpt": "- CMB-val: 280 questions with solutions and explanations; used as source for CoT and few-shot",
      "snapshot_id": "s01",
      "scope": {
        "en": "validation set (280)",
        "zh": "验证集 280 题"
      }
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "author-stated",
      "excerpt": "- CMB-test: 400 questions per subcategories, 11200 questions in total",
      "snapshot_id": "s01"
    },
    {
      "facet": "benchmark_status",
      "value": "public-leaderboard",
      "basis": "author-stated",
      "excerpt": "## 🥇 Leaderboard",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "json",
      "basis": "author-stated",
      "excerpt": "path: CMB-Exam/CMB-test/CMB-test-choice-question-merge.json",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "author-stated",
      "excerpt": "# CMB: A Comprehensive  Medical Benchmark in Chinese",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Recorded the code repository license separately; it is not treated as a data license statement.",
        "zh": "单独记录代码仓库许可证，不视为数据许可声明。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 11 (9 stated by the authors with excerpts, 2 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 11 个（作者声明 9 个，附逐字摘录；据内容推断 2 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: multi-specialty(author-stated).",
        "zh": "新增专科标签：multi-specialty(author-stated)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/CMB",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/CMB",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/.gitattributes",
        "size_bytes": 2383,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "CMB-Clin-qa.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Clin-qa.json",
        "size_bytes": 259904,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Clin/CMB-Clin-qa.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Clin/CMB-Clin-qa.json",
        "size_bytes": 259904,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Clin/a",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Clin/a",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "CMB-Exam/CMB-test/CMB-test-choice-hierarchy.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-test/CMB-test-choice-hierarchy.json",
        "size_bytes": 1278,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-test/CMB-test-choice-question-merge.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-test/CMB-test-choice-question-merge.json",
        "size_bytes": 6009783,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-test/a",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-test/a",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "CMB-Exam/CMB-train/CMB-train-hierarchy.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-train/CMB-train-hierarchy.json",
        "size_bytes": 1323,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-train/CMB-train-merge.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-train/CMB-train-merge.json",
        "size_bytes": 148473163,
        "checksum": {
          "algorithm": "sha256",
          "value": "6539cb96d81e0672d18b0ea255b2f040dda2ec90095916d7620969d0ce8eb01d"
        },
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-train/a",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-train/a",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "CMB-Exam/CMB-val/CMB-val-hierarchy.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-val/CMB-val-hierarchy.json",
        "size_bytes": 1005,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-val/CMB-val-merge.json",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-val/CMB-val-merge.json",
        "size_bytes": 600626,
        "checksum": null,
        "format": "json"
      },
      {
        "name": "CMB-Exam/CMB-val/a",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/CMB-val/a",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "CMB-Exam/a",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-Exam/a",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "CMB-datasets.zip",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/CMB-datasets.zip",
        "size_bytes": 30079706,
        "checksum": {
          "algorithm": "sha256",
          "value": "246acbb40a4406b7c5457ad885379f76c24cdf7d3487adcdb17d8d8d557221b7"
        },
        "format": "zip"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/README.md",
        "size_bytes": 8713,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "assets/CMB-2.svg",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/assets/CMB-2.svg",
        "size_bytes": 254839,
        "checksum": null,
        "format": "svg"
      },
      {
        "name": "assets/CMB-final.png",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/assets/CMB-final.png",
        "size_bytes": 1042518,
        "checksum": {
          "algorithm": "sha256",
          "value": "1ac0f8261ff0d0f2e4cfef7d44d48b7a5541e5a7f769a318b143bf1f82e62ccb"
        },
        "format": "png"
      },
      {
        "name": "assets/CMB-qa.png",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/assets/CMB-qa.png",
        "size_bytes": 343617,
        "checksum": {
          "algorithm": "sha256",
          "value": "65f9bfb0b5a8bf56f18a00b98c84a03dc890d2b0f78a8d592c0304205e4ec146"
        },
        "format": "png"
      },
      {
        "name": "assets/test",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/assets/test",
        "size_bytes": 0,
        "checksum": null,
        "format": null
      },
      {
        "name": "assets/title.png",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/CMB/resolve/935fbc09edf1303d89872b21265ff597f426ac0d/assets/title.png",
        "size_bytes": 118573,
        "checksum": {
          "algorithm": "sha256",
          "value": "645e4f830d2a40d0a11e2f1d843f814223ab389998d8924f7d4d9693758ab81e"
        },
        "format": "png"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/CMB --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "935fbc09edf1303d89872b21265ff597f426ac0d",
      "last_modified": "2024-04-05T16:10:47.000Z"
    },
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": []
  },
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: MedMCQA (https://mdexa.com/datasets/medmcqa/); 医学考试题库 JSON 数据集 (https://mdexa.com/datasets/medical-exam-question-bank-json/); DiagnosisArena (https://mdexa.com/datasets/diagnosisarena/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "MedMCQA",
        "url": "https://mdexa.com/datasets/medmcqa/",
        "json": "https://mdexa.com/datasets/medmcqa.json"
      },
      {
        "name": "医学考试题库 JSON 数据集",
        "url": "https://mdexa.com/datasets/medical-exam-question-bank-json/",
        "json": "https://mdexa.com/datasets/medical-exam-question-bank-json.json"
      },
      {
        "name": "DiagnosisArena",
        "url": "https://mdexa.com/datasets/diagnosisarena/",
        "json": "https://mdexa.com/datasets/diagnosisarena.json"
      }
    ]
  }
}