ResearchTasksSafety and Action BlockingSafety and Action BlockingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAutomated Batch Evaluation N=100Aethelgard87Total Tool Calls1Apr 15, 2026Automated Batch Evaluation N=500Aethelgard447Total Tool Calls1Apr 15, 2026