ResearchTasksInstruction Adherence and Security RobustnessInstruction Adherence and Security RobustnessFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedStruQ 1.0 (Adversarial)Text85.46Capability Score4Feb 26, 2026StruQ Clean 1.0Text84.87Capability Score4Feb 26, 2026