williamliujl/CMExam

A Chinese National Medical Licensing Examination dataset and large languge model benchmarks

41
/ 100
Emerging

This project provides a comprehensive dataset of over 60,000 multiple-choice questions from the Chinese National Medical Licensing Examination. It's designed to help researchers and developers assess how well large language models can perform on complex medical knowledge tasks. You input Chinese medical exam questions, and it helps you evaluate how accurately different AI models can answer them, along with detailed annotations like disease groups and difficulty levels. This is for AI researchers and medical informatics professionals who are developing or benchmarking AI models for medical applications.

No commits in the last 6 months.

Use this if you are developing or evaluating AI models that need to demonstrate robust knowledge in the medical domain, specifically with Chinese medical content.

Not ideal if you need a dataset for assessing individual medical competence, patient diagnosis, or if your primary interest is in non-textual or multimodal medical questions (though a related multimodal dataset exists).

medical-education AI-benchmarking medical-informatics natural-language-processing medical-licensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

84

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Dec 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/williamliujl/CMExam"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.