ResearchTasksAccess Control EnforcementAccess Control EnforcementFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated200 Adversarial Tool-Use Tasks 1.0 (test)Claude Haiku 3.568.5UIR9May 19, 2026MULTIPER-ENTERPRISEAAAC0.005PVR9Feb 26, 2026