ResearchTasksDeception EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSycophancyGRPO89.77CoT Plan Accuracy6Mar 31, 2026Strategic DeceptionGRPO28.86CoT Plan Fidelity6Mar 31, 2026