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

ZeroBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal reasoningZeroBench main
Pass@111
13
General Reasoning & UnderstandingZeroBench
Accuracy18.9
8
Multimodal reasoningZeroBench sub
Pass@130.8
7
Multimodal reasoningZeroBench
Accuracy25.15
6
Showing 4 of 4 rows