ResearchDatasetsor_benchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-label Safety Categorizationor_bench 80k72.54Macro Accuracy8Multi-label Safety Categorizationor_bench hard 1k53.53Macro Accuracy4