ResearchDatasetsFlamesFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMoral Alignment EvaluationFlames Benchmark953PSC1 Score73Moral Alignment evaluationFlames755Win Count72Core Value AlignmentFlames99.5Score5Jailbreak Success Rateflames38.6Success Rate (Raw)3