ResearchTasksHarmful-request assistanceFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSORRY-Bench linguistic mutationsQwen3.5-27B25.4Compliance Rate6Jun 9, 2026SORRY-Bench decontaminated base promptsQwen3.5-27B17.1Compliance Rate6Jun 9, 2026