ResearchTasksEthical Robustness EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedERTS 1.0 (test)Gemini-2.0-Flash94ERS6Jun 12, 2026AMST (Adversarial Multi-round Stress Testing) (post-stress)GPT-4o0.93Mean Robustness3Apr 2, 2026Ethical RobustnessLLaMA-3-8B0.62Mean Robustness (μR)3Apr 2, 2026