Inference
EN

HealthBench Professional raw score

Raw score on physician-authored clinical consult, documentation, and research conversations.

ModelsModels with a result.8
Top resultBest result on this benchmark.—
Top-3 spreadPoints from first to third.—
YearYear of release.—

Result and price

8 of 8 results

Results

8 results
#ModelResultThe score from the source.
—Claude Opus 5.577.1%
—Claude Sonnet 5.577.1%
—Claude Opus 573.4%
—GPT-6 Astra68.2%
—GPT-6.1 Sol67.2%
—GPT-6.1 Terra64.2%
—GPT-6 Luna61.2%
—GPT-6 Sol59.5%