ResearchTasksJailbreak Attack Safety EvaluationJailbreak Attack Safety EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGPT-as-a-JudgePCSA89ASR40Apr 7, 2026CARES adversarial mental-health targets 2025AMA84Success Score (SS)40Apr 7, 2026