Usmle Aligned Clinical Knowledge Evaluation Via Multiple Choice Question Answering

via “usmle-aligned clinical knowledge evaluation via multiple-choice question answering”

12.7K USMLE medical exam questions for clinical AI evaluation.

Unique: Directly sourced from or aligned with actual USMLE examination questions rather than synthetic or web-scraped medical Q&A; includes all three USMLE steps with validated answer keys and multilingual variants (English, simplified Chinese, traditional Chinese), making it the only dataset that directly mirrors the licensing exam format physicians must pass

vs others: More clinically rigorous and regulatory-relevant than general medical QA datasets (e.g., PubMedQA) because it uses actual licensing exam questions, enabling direct comparison of LLM performance to human physician passing scores and regulatory thresholds