Benchmark

MedQA (USMLE)

Measures: Multiple-choice medical licensing exam questions (USMLE-style), scored by accuracy; Vals' version also tests robustness to biased question variants.

Maintainer
Jin et al. (original dataset); Vals AI ran the independent leaderboard
Introduced
2020
Status
Unmaintained
Saturation
Saturated
Typical provenance
Mixed
In scoring set
No

Paper

Leaderboard

Independent and third-party results only.

No independent or third-party results yet. Show all results