US medical licensing exam style questions. The original medical LLM benchmark and still the most cited.

MedQA is a benchmark in healthcare AI. US medical licensing exam style questions. The original medical LLM benchmark and still the most cited. Scores are reported as: Percent accuracy, multiple choice.

Audited by MedCheckJin et al., Applied Sciences 2021

Key facts

What it measuresUS medical licensing exam style questions. The original medical LLM benchmark and still the most cited.
Who should careResearchers comparing to prior literature.
Use it whenYou need comparability with years of published results.
Do not use it forPredicting clinical performance. Exam scores correlate poorly with real clinical utility, and contamination risk is high after years of reuse.
Score scalePercent accuracy, multiple choice.
Grader methodunknown
First released2021
LanguagesEnglish, Chinese
Use casesexam knowledge
CitationJin et al., Applied Sciences 2021
Statusactive

Frequently asked questions

What does MedQA measure?

US medical licensing exam style questions. The original medical LLM benchmark and still the most cited.

Who should use MedQA?

Researchers comparing to prior literature. You need comparability with years of published results.

What should MedQA not be used for?

Predicting clinical performance. Exam scores correlate poorly with real clinical utility, and contamination risk is high after years of reuse.

How are MedQA scores reported?

Percent accuracy, multiple choice. Scores from different benchmarks are not comparable to each other.

Is MedQA independent?

No conflicts of interest have been verified for MedQA in this registry as of 2026-08-05. Absence of a recorded conflict means none has been verified, not that none exists.

Compare with

AfriMed-QA

Multi-specialty medical questions written by clinicians and students across African countries, built to test w

CHBench

Chinese-language evaluation of physical and mental health knowledge in large models.

CMB

Comprehensive Chinese medical benchmark spanning exam knowledge and clinical case work.

CMExam

Chinese medical licensing exam questions with expert annotations for reasoning and difficulty.

COGNET-MD

Evaluation framework and dataset covering several medical specialties, built around clinician-style diagnostic

HeadQA

Spanish healthcare specialization exam questions requiring multi-step reasoning.

Last verified 2026-08-05. Governance and conflict data compiled by Healthcare Discovery from primary sources, each linked above. Seed inventory from Ma et al., Beyond the Leaderboard, ACL 2026. How we verify · All 63 entities