Benchmark
MultiMedBench
A multi-task medical AI evaluation benchmark covering a range of clinical question-answering scenarios, with licensed physicians involved in annotation and review. It is used to assess the comprehensive capabilities of large medical AI models.
Timeline (last 90 days)
Sep 23
Both MedQA and MultiMedBench involve licensed physicians in annotation and review, setting a precedent for the expert-informed design pattern in medical AI evaluation.
Unverified50%