Get started Console

Modern medicine75

Traditional medicine24

Cross-cutting12

Collections

Models8

License status and Mdexa hosting, recorded separatelyAll datasets

CBLUE

Verified by Mdexa · Checked against the source text under public rules.How we check

Commercial use
UnclearUnstated
Derivatives
UnclearUnstated
Redistribution
UnclearUnstated
File on Mdexa
NoPending

Only a code repository license

UnstatedPendingNOASSERTIONSave

Badge

Mdexa verified · Unstated · 2026-11Mdexa verifiedUnstated · 2026-11

[![Mdexa verified · Unstated · 2026-11](https://mcp.mdexa.com/v1/badge/datasets/cblue.svg)](https://mdexa.com/datasets/cblue/)

Place it on a repository or dataset page; the status and date follow the verification. About badges

Cite this pageMdexa, CBLUE, https://mdexa.com/datasets/cblue/, verified 2026-11-12.

Key facts

Domain
Clinical medicine Modern medicine
Content
Question banks and benchmarks · Annotated corporaBenchmark (8 Chinese biomedical language understanding tasks)
Size
  • 8 taskstasks
  • 23,000 itemsCMeEE
  • 22,406 itemsCMeIE
  • 18,192 itemsCHIP-CDN
  • 30,000 itemsCHIP-STS
  • 40,644 itemsCHIP-CTC
  • 10,830 itemsKUAKE-QIC
  • 32,552 itemsKUAKE-QTR
  • 18,196 itemsKUAKE-QQR
As stated: 8个任务：CMeEE 23,000、CMeIE 22,406、CHIP-CDN 18,192、CHIP-STS 30,000、CHIP-CTC 40,644、KUAKE-QIC 10,830、KUAKE-QTR 32,552、KUAKE-QQR 18,196（训/验/测合计）
Language / modality
Chinese / Text
Publisher
中国多家高校与机构（ACL 2022 论文，Ningyu Zhang 等）
Year
2022
Expert review
Not stated
Verification
Verified: no license statement on the page

Commercial use of CBLUE

Commercial use: Unclear (Unstated). License status: Unstated.

Quoted statements and their sources are in CBLUE license evidence.

Verdicts record what sources state and are not legal advice.

Tags

Task format
Named entity recognition

Quoted from the sourceThe evaluation task is the recognition of the named entity on the medical text. Given schema data and medical sentences, models are expected to extract entity about cliSnapshot s01

Relation extraction

Quoted from the source| CMeIE | Relation Extraction | 14,339 | 3,585 | 4,482 | Micro F1 |Snapshot s01

Term normalization

Quoted from the sourceThe evaluation task is the normalization of the diagnosis entity from the Chinese medical record. Given a diagnosis entity, models are expected to return corresponding standard terms.Snapshot s01

Text classification

Quoted from the source| CHIP-CTC | Sentence Classification | 22,962 | 7,682 | 10,000 | Macro F1 |Snapshot s01

Text matching

Quoted from the source| CHIP-STS | Sentence Similarity | 16,000 | 4,000 | 10,000 | Macro F1 |Snapshot s01

Intended use
Evaluation

Quoted from the sourceWe evaluate the current 11 Chinese pre-trained models on the eight biomedical language understanding tasks and report the baselines of these tasks.Snapshot s01

Specialty
Multi-specialty
Data format
JSON

Quoted from the source| └── {Task}_train.jsonSnapshot s01

Official split
Train and test splits

Quoted from the source| └── {Task}_dev.jsonSnapshot s01

Author-statedInferredHuman-confirmed

CBLUE license evidence 2

No data license stated

Code repository license: Apache-2.0. This licenses the repository, not the data; the data has no separate statement. LICENSE file · verified s02

  1. Repository license filePage opened
    Apache-2.0
    Third-party text · Repository license fileApache License Version 2.0, January 2004

    GitHub repository license: Apache-2.0 (code and data not distinguished)

    github.com2026-11-12 · s02
  2. READMEPage opened

    README states no data license; data hosted on Tianchi, download-page terms not opened [Note: No license statement seen in snapshot s01, s02, s03]

    github.com2026-11-12

Source and lineage

Real biomedical scenario data (README description)

Known issues with CBLUE

  • Data is downloaded via Tianchi; the download page terms were not opened this time
  • Code license and data license are not distinguished

Preflight

Not run Runs only on ingested data; says nothing about quality.

Downloading CBLUE and API access

No file on Mdexa (see the verdict). Get it from the source and confirm the terms there:

Citing CBLUE

Mdexa, CBLUE, https://mdexa.com/datasets/cblue/, verified 2026-11-12.
More citation details

The source gives no citation text; the line above cites this card.

Machine-readable

cblue.jsoncblue.mdcatalog.json

Change log 8
2026-11-13Added specialty tags: multi-specialty(inferred).
2026-11-13Added the data_format tag (json), based on the file layout of the repository.
2026-11-13Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.
2026-11-13Added dataset-level tags: 8 (7 stated by the authors with excerpts, 1 inferred from the content). No conclusion changed.
2026-11-12Recorded the code repository license separately; it is not treated as a data license statement.
2026-11-12Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.
2026-11-12License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.
2026-11-12Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.

Listed in

Datasets similar to CBLUE

  • PromptCBLUEVerified by MdexaNamed entity recognitionEvaluation RestrictedLink only 68.9K items

    License is restricted: README prohibits commercial use; link only.

    Clinical medicine · Question banks and benchmarks · Annotated corpora · Derived

    Open the cardSave

    Shared: Task format Named entity recognition, Relation extraction, Term normalization, Text classification · Intended use Evaluation · Official split Train and test splits · Specialty Multi-specialty · domain Clinical medicine · content Question banks and benchmarks, Annotated corpora

  • IMCS-21Verified by MdexaPediatricsMulti-turn dialogueEvaluation UnstatedPending 4,116 records

    License unstated: No license on the repository page; link only until resolved.

    Clinical medicine · QA, dialogue and instruction data · Annotated corpora · Real patient text

    Open the cardSave

    Shared: Task format Named entity recognition, Text classification · Intended use Evaluation · domain Clinical medicine · content Annotated corpora

  • PubMedCausalVerified by MdexaRelation extractionEvaluationReviewed, method unspecified PermissiveLink only —

    License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Link only.

    Biomedical literature · Annotated corpora · Literature

    Open the cardSave

    Shared: Task format Relation extraction, Text classification · Intended use Evaluation · Official split Train and test splits · Specialty Multi-specialty · system Modern medicine · content Annotated corpora

  • PMC-Patients-ReCDSVerified by MdexaText matchingEvaluation RestrictedLink only —

    License restricted: restrictions are read broadly: CC-BY-NC-SA-4.0. Risk flag(s): derived, Real patient text. Link only.

    Clinical medicine · Biomedical literature · Annotated corpora · Clinical cases · Literature · Derived · Real patient text

    Open the cardSave

    Shared: Task format Text matching · Intended use Evaluation · Official split Train and test splits · Specialty Multi-specialty · domain Clinical medicine · content Annotated corpora

  • CMBChinese Medical BenchmarkVerified by MdexaMultiple-choice (single answer)EvaluationWith explanations PermissiveLink only 11.2K questions

    License is permissive, but source risk: questions come from copyrighted exams; link only.

    Clinical medicine · Question banks and benchmarks · Clinical cases · Exam-derived

    Open the cardSave

    Shared: Intended use Evaluation · Official split Train and test splits · Data format JSON · Specialty Multi-specialty · domain Clinical medicine · content Question banks and benchmarks