ResearchTasksOracle Poisoning SusceptibilityFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOracle Poisoning Scenario 3 L2 Real SDK tool-use prefix-free (N=30)Claude Sonnet 4.6100Trust10May 12, 2026
Oracle Poisoning Scenario 3 L2 Real SDK tool-use prefix-free (N=30)Claude Sonnet 4.6100Trust10May 12, 2026