ResearchTasksVulnerability Attack PerformanceFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedE2E Cross-domain (dev)Gemini-3 Flash0.833ASR (E-commerce) (CodeQL)6Feb 26, 2026E2E (dev)Gemini-3 Pro100ASR (Semgrep) - E-commerce6Feb 26, 2026