MedAgents-Bench

What is MedAgents-Bench?

MedAgentsBench features 862 challenging medical questions from seven datasets, focusing on cases where models struggle. It emphasizes multi-step clinical…

Released

2025-03-16

Evaluates

推理, Reasoning, 知识, Knowledge, Medical, Agent, 科学智能, AI for Science, 逻辑推理, 知识储备, 科学推理, Scientific Reasoning, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MedAgents-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2503.07459
• Code https://github.com/gersteinlab/medagents-benchmark
• Dataset https://huggingface.co/datasets/super-dainiu/medagents-benchmark

Which sources cite MedAgents-Bench?

• MedAgents-Bench

Related 推理, Reasoning, 知识, Knowledge, Medical, Agent, 科学智能, AI for Science, 逻辑推理, 知识储备, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks

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