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

MM-BrowseComp

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal SearchMM-BrowseComp (MMBC)
Success Rate30.1
15
Multimodal SearchMM-BrowseComp
Accuracy10.8
14
Multimodal long-horizon complex reasoningMM-BrowseComp
Score41.1
13
Multimodal SearchMM-BrowseComp (test)
Accuracy16.1
12
Multimodal SearchMM-BrowseComp
Score46.3
10
Vision Agent CapacityMM-BrowseComp
Score48.8
6
Visual SearchMM-BrowseComp
Pass@146.3
4
Showing 7 of 7 rows