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

Search-R1

Benchmarks

Task NameDataset NameSOTA ResultTrend
Interval QualitySearch-R1
Hit Rate36.5
5
Task PerformanceSearch-R1
Success Rate75.8
5
Question AnsweringSearch-R1 generalization tasks Average
EM31.3
2
Showing 3 of 3 rows