ResearchTasksTarget behavior attackTarget behavior attackFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMBPPAiTM99.2ASR16Feb 26, 2026HumanEvalAiTM98.3ASR16Feb 26, 2026MMLU phyAiTM99.3ASR16Feb 26, 2026MMLU bioAiTM98.4Attack Success Rate (ASR)16Feb 26, 2026SoftwareDevAiTM1Attack Success Rate8Feb 26, 2026