ResearchDatasetsStandard Disallowed Content EvaluationFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSafety EvaluationStandard Disallowed Content Evaluation (test)100Hate Speech Aggregate Accuracy4Disallowed Content EvaluationStandard Disallowed Content Evaluation99.6Hate (Aggregate)4