ResearchDatasetsAutoRANFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsHarmfulness EvaluationAutoRAN1.32Harmfulness Score22Jailbreak RobustnessAutoRAN0Harmfulness Rate17Jailbreak Attack DefenseAutoRAN0Reasoning Failure Rate (FFR)17