Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MEDREASON

Benchmarks

Task NameDataset NameSOTA ResultTrend
Clinical ReasoningMEDREASON
Pass@173.4
15
Medical ReasoningMEDREASON
Best-of-16 Delta (Δ)16.4
6
Showing 2 of 2 rows