ResearchTasksOut-of-distribution (OOD) Harmful Content DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedJailbreakBenchw_opt0.962AUROC (Alpaca)1Apr 23, 2026HarmBenchw_opt0.961AUROC (vs Alpaca)1Apr 23, 2026AdvBenchw_opt99.2AUROC (vs Alpaca)1Apr 23, 2026