ResearchDatasetsSkillResolve-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSkill retrievalSkillResolve-Bench 1.0 (test)76.6Recall@35Skill RetrievalSkillResolve-Bench 1.0 (held-out pairs)91.1R@205