ResearchDatasetsASSEBenchASSEBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAgent SafetyASSEBench92.04Accuracy69Agent Safety ReasoningASSEBench-Corrected84.72Accuracy25Safety classificationASSEBench92.04Accuracy20Safety classificationASSEBench (test)89.97Accuracy12