ResearchDatasetsSEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPrompt classificationSEval92.5F1 Score16Safe CompletionSEval Response 2.080.8F1 Score16Safe CompletionSEval Prompt 2.093.7F1 Score16