shaafsalman/medagentbench-tasks download history

shaafsalman/medagentbench-tasks is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 73 times (28 in the last 7 days), and 365 times in total. It ranks #142,324 among datasets by monthly downloads.

MedAgentBench-Tasks The official evaluation task set for MedAgentBench — a Stanford clinical LLM benchmark. Contains 300 FHIR-based agentic tasks across 10 clinical task types, designed to evaluate language models on real EHR workflows via a live FHIR REST API. Paper: MedAgentBench (

Open shaafsalman/medagentbench-tasks on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.