ResearchTasksMulti-turn Jailbreak DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHarmBench and DEFCON Multi-turn Jailbreak N=1,010 (test)DeepContext84F1 Score10Feb 26, 2026