ResearchDatasetsResponse-side Safety BenchmarksResponse-side Safety BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety GuardrailResponse-side safety benchmarks87F1 Score12Response-side Safety ClassificationResponse-side Safety Benchmarks HarmB, SafeRLHF, BeaverTails, XSTest, Aegis2, WildG, Think98.5HarmB Score12
Response-side Safety ClassificationResponse-side Safety Benchmarks HarmB, SafeRLHF, BeaverTails, XSTest, Aegis2, WildG, Think98.5HarmB Score12