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

PhysReason

Benchmarks

Task NameDataset NameSOTA ResultTrend
Open-ended Question AnsweringPhysReason v2 (test)
Subpart-AND (v2)51.1
9
Physics ReasoningPhysReason
Overall Score73.3
4
Showing 2 of 2 rows