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

WebSearch

Benchmarks

Task NameDataset NameSOTA ResultTrend
Web searchWebSearch GRADUAL
F1 Score63.6
8
Web searchWebSearch (ROTATION)
F1 Score66.7
8
Web searchWebSearch STEP
F1 Score69.7
8
Showing 3 of 3 rows