Dataset · FreedomIntelligence
Chinese medical benchmark
FreedomIntelligence/CMB
Comprehensive test set of medical questions and answers for evaluating language models in Chinese.
What's inside
A text dataset of fewer than 1,000 examples in Chinese, representing a medical benchmark for question-answering and text generation tasks. It includes test items from the CMB-Exam section with revealed and verified answers, and the dataset itself is included in the OpenCompass evaluation system.
What you can do with it
- Evaluating medical knowledge and LLM response accuracy in Chinese
- Comparing models within the OpenCompass benchmark
- Tasks
- Question answering, Text generation
- Languages
- Chinese
- Size
- up to 1K rows
- Downloads this month
- 3K
- Likes
- 38
Models trained on it
How to load it
from datasets import load_dataset
ds = load_dataset("FreedomIntelligence/CMB")