ResearchTasksSub-task CompletionSub-task CompletionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAI-Pentest-Benchmark Single ExperimentQwen3-32B-finetune (Ours)46AC Score7Apr 28, 2026AutoPenBenchQwen3-32B-finetune212AC (Count)7Apr 28, 2026