EvaluateBM: a multi-agent framework for evaluating reasoning-capable language models in biomedical tasks
收藏官方服务：
资源简介：
This is the visualization code and data of four biomedical tasks: clinical QA (MedMCQA), evidence extraction (PubMedQA), gene set functional annotation, and cell type identification for manuscript "EvaluateBM: a multi-agent framework for evaluating reasoning-capable language models in biomedical tasks"
提供机构：
Zenodo创建时间：
2026-03-04
