ResearchDatasetsHEx-PHI, AdvBench, HarmBench, & JailbreakBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHarmfulness EvaluationHEx-PHI, AdvBench, HarmBench, & JailbreakBench Full4.95Average Score (Full)6