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

SkillResolve-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Skill retrievalSkillResolve-Bench 1.0 (test)
Recall@376.6
5
Skill RetrievalSkillResolve-Bench 1.0 (held-out pairs)
R@2091.1
5
Showing 2 of 2 rows