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

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.