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

LiveVQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringLiveVQA
Accuracy77.7
151
Multimodal Question AnsweringLiveVQA
Pass@170.5
24
Multimodal SearchLiveVQA
Accuracy84.1
19
Multimodal long-horizon complex reasoningLiveVQA
Score81.3
15
Showing 4 of 4 rows