Benchmark
MedQA
Test medical knowledge and reasoning using professional medical-board exam questions.
Explore the original evidence
Explore the original evaluation, its methods, and reported findings.
Open evalCoverage
12,723 English, 34,251 simplified-Chinese, and 14,123 traditional-Chinese medical-exam questions in the original dataset.
Methodology
Choose an answer to a medical-exam question. Preserve language, official split, answer-option version, retrieval context, and prompting setup when comparing accuracy.