ResearchTasksLLM ModerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWildGuardMix (test)MLPM Simple Refuse14.59ASR28Jun 2, 2026LLM Moderation (Evaluation Set)MLPM90.23F1 Score9Jun 2, 2026