ResearchDatasetsHarmBench and JailbreakBenchHarmBench and JailbreakBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAdversarial AttackHarmBench (HB) and JailbreakBench (JBB) (held-out prompts)72.1ASR (%)36