ResearchDatasetsGeneral-domain safety benchmarksGeneral-domain safety benchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsResponse-level safety classificationGeneral-domain safety benchmarks Response-Level86.79F1 Score7Query-level safety classificationGeneral-domain safety benchmarks Query-Level86.78F1 Score7