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

BrowseComp-EN

Benchmarks

Task NameDataset NameSOTA ResultTrend
Deep ResearchBrowseComp-EN (BC-en) original (test)
Pass@149.7
20
Web ResearchBrowseComp-EN 200
Pass@114.5
19
Showing 2 of 2 rows