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

Single-Objective Tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Single-Objective TaskSingle-Objective Tasks (2WikiMultihopQA, HotpotQA, Bamboogle, Frames, BrowseComp-Plus)
Accuracy (2WikiMultihopQA)77.5
9
Showing 1 of 1 rows