ResearchDatasetsSafety SuiteSafety SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety EvaluationSafety Suite AdvBench, PKU-SafeRLHF, HarmBench, JailbreakBench, SORRY-Bench, HarmfulQA, ALERT8.59AdvBench Score56
Safety EvaluationSafety Suite AdvBench, PKU-SafeRLHF, HarmBench, JailbreakBench, SORRY-Bench, HarmfulQA, ALERT8.59AdvBench Score56