MTCMB Benchmark

What is MTCMB?

We introduce MTCMB-a Multi-Task Benchmark for Evaluating LLMs on TCM Knowledge, Reasoning, and Safety. Developed in collaboration with certified TCM experts…

Released

2025-05-15

Evaluates

推理, Reasoning, 知识, Knowledge, 理解, Understanding, Chinese Medicine, Benchmark, TCM, 科学智能, AI for Science, 逻辑推理, 知识储备, 语言理解, Comprehension, 科学推理, Scientific Reasoning, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MTCMB

MTCMB code and dataset

• Code https://github.com/Wayyuanyuan/MTCMB
• Dataset https://huggingface.co/datasets/Bunnybeck/MTCMB

Which sources cite MTCMB?

• MTCMB

Related 推理, Reasoning, 知识, Knowledge, 理解, Understanding, Chinese Medicine, Benchmark, TCM, 科学智能, AI for Science, 逻辑推理, 知识储备, 语言理解, Comprehension, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench