ResearchTasksRefusal DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAlpaca + XSTest (val)wopt0.988AUROC42Apr 23, 2026WILDGUARD (test)WILDGUARD94F1 (Harmful)14Feb 26, 2026Do-Not-Answer Portuguese (test)gov.pt baseline100Accuracy9Mar 4, 2026XSTEST-RESP (full)GPT-498.1RR (F1)9Feb 26, 2026XSTest Refusal OOD (test)ACS Refusal Probe100MC Recall7May 12, 2026JailbreakBench Refusal OOD (test)ACS Refusal Probe100MC Recall7May 12, 2026