USMLE / MedQA Benchmark

Explore score history ↗

USMLE / MedQA is an AI benchmark in the Benchmark Radar catalog.

Released: 2020-09-29
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

USMLE / MedQA results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
GPT 5	—	96.32	—	evidence
GPT 5 Mini	—	96.06	—	evidence
GPT 5.1	—	96.38	—	evidence
o1	—	96.52	—	evidence
o3	—	96.06	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite USMLE / MedQA?

USMLE / MedQA