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

PhysBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Physical ReasoningPhysBench
S1 Score97.1
13
Physical PerceptionPhysBench
PhysBench Score64.4
9
Visual Question AnsweringPhysBench
Accuracy58.3
6
Showing 3 of 3 rows