ResearchDatasetsSafety Benchmarks and WildJailbreakSafety Benchmarks and WildJailbreakFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety EvaluationSafety Benchmarks (Aggregate) and WildJailbreak (test)95.7Safety Score21