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

RWQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringRWQA
Accuracy80.8
30
Visual Question AnsweringRWQA 158 (val)
Score80.8
23
Multimodal Multi-choiceRWQA
Accuracy70.5
14
Real-world Spatial UnderstandingRWQA
Top-1 Accuracy67.84
10
Real-world Multi-modal Question AnsweringRWQA
Accuracy70.46
4
Showing 5 of 5 rows