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

YesBut

Benchmarks

Task NameDataset NameSOTA ResultTrend
Humor DetectionYesBut
Accuracy70.4
21
Multimodal Humor ExplanationYesBut
Precision77.3
20
Visual Question AnsweringYesBut
Accuracy62.9
8
Showing 3 of 3 rows