ResearchTasksRobustness against harmful content generationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLMSYS harmful queriesRLBF1Attack Success Rate20Feb 26, 2026LMSYS-MF attacksIT0.81Attack Success Rate20Feb 26, 2026