Get started Console

Modern medicine75

Traditional medicine24

Cross-cutting12

Collections

Models8

License status and Mdexa hosting, recorded separatelyAll datasets

PromptCBLUE

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

Commercial use
No
Derivatives
UnclearUnstated
Redistribution
UnclearUnstated
File on Mdexa
NoLink only

README prohibits commercial use

RestrictedLink onlyNOASSERTIONSave

Badge

Mdexa verified · Restricted · 2026-11Mdexa verifiedRestricted · 2026-11

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

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

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

Source riskDerived

Key facts

Domain
Clinical medicine Modern medicine
Content
Question banks and benchmarks · Annotated corporaBenchmark (prompt-formatted multi-task version of CBLUE)
Size
  • 68,900 itemsv0.2 train
  • 10,360 itemsv0.2 validation
  • 10,320 itemsv0.2 Test A
  • 10,320 itemsv0.2 Test B
  • 94 itemsprompt templates
As stated: v0.2：训练68,900、验证10,360、Test A 10,320、Test B 10,320；94个提示模板
Language / modality
Chinese / Text
Publisher
michael-wzhu 等（CCKS/天池评测）
Year
2023
Expert review
Not stated
Verification
Verified: no license statement on the page

Commercial use of PromptCBLUE

Commercial use: No. License status: Restricted.

Quoted statements and their sources are in PromptCBLUE license evidence.

Verdicts record what sources state and are not legal advice.

Tags

Task format
Named entity recognitionRelation extractionTerm normalizationText classification
Intended use
Evaluation

Quoted from the sources://tianchi.aliyun.com/dataset/95414)基准进行二次开发，将16种不同的医疗场景NLP任务全部转化为基于提示的语言生成任务,形成首个中文医疗场景的LLM评测基准。**PromptCBLUE**作为CCKS-2023的评测任务之一，已在阿里巴巴天池大赛平台上线进行开放评测，欢迎各位师生报名参赛(刷榜)。Snapshot s01

Specialty
Multi-specialty
Data format
JSONL

Quoted from the sourcePromptCBLUE中将各个任务都已经转化为了根据prompt生成回复的统一格式，测试样本在[test.json](./datasets/toy_examples/test.json)文件中，这个文件采用json line格式，每行是一个可json化的字符串，json化后"input"字段作为LLM输入，"target"字段为空字符串，待选手们填入模型回复。Snapshot s01

Official split
Train and test splits
Benchmark status
Public leaderboard

Quoted from the source- 在CCKS-2023会议后，PromptCBLUE将作为天池数据集，长期开放榜单，供社区评测/打榜。Snapshot s01

Author-statedInferredHuman-confirmed

PromptCBLUE license evidence 2

  1. Repository sidebarPage opened

    Repository page shows no license [Note: No license statement seen in snapshot s01, s02]

    github.com2026-11-12
  2. READMEPage opened
    Third-party text · README本项目相关资源仅供学术研究之用，严禁用于商业用途。

    README non-commercial statement

    github.com2026-11-12 · s01

Source and lineage

CBLUE tasks rewritten into prompt format

Known issues with PromptCBLUE

  • Underlying data comes from CBLUE; CBLUE data terms must be checked as well
  • Competition rules forbid calling public model APIs directly to predict the test set

Preflight

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

Downloading PromptCBLUE and API access

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

The terms are restricted; no download command is given. See the verdict.

Citing PromptCBLUE

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

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

Machine-readable

promptcblue.jsonpromptcblue.mdcatalog.json

Change log 6
2026-11-13Added specialty tags: multi-specialty(inferred).
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: 9 (3 stated by the authors with excerpts, 6 inferred from the content). No conclusion changed.
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 PromptCBLUE

  • CBLUEVerified by MdexaNamed entity recognitionEvaluation UnstatedPending 8 tasks

    License unstated: Only a code repository license; no data license stated; link only until resolved.

    Clinical medicine · Question banks and benchmarks · Annotated corpora

    Open the cardSave

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

  • ESL-benchEvent-driven Synthetic Longitudinal BenchmarkVerified by MdexaOpen-ended QAEvaluationWith explanations ConflictPending —

    License conflict: the publisher's own statements contradict each other (permissive license vs restriction). Link only.

    Clinical medicine · Question banks and benchmarks · Knowledge graphs

    Open the cardSave

    Shared: Intended use Evaluation · Benchmark status Public leaderboard · Data format JSONL · Specialty Multi-specialty · domain Clinical medicine · content Question banks and benchmarks

  • MedMCQAVerified by MdexaMultiple-choice (single answer)Fine-tuningWith explanations PermissiveLink only —

    License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Risk flag(s): Exam-derived, scraped. Link only.

    Clinical medicine · Question banks and benchmarks · QA, dialogue and instruction data · Exam-derived · Scraped

    Open the cardSave

    Shared: Intended use Evaluation · Benchmark status Public leaderboard · Official split Train and test splits · Specialty Multi-specialty · domain Clinical medicine · content Question banks and benchmarks