ResearchDatasetsPACEbenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCybersecurity knowledge assessment and autonomous exploitationPACEbench v2.0 (test)59A-CVE Success Rate10
Cybersecurity knowledge assessment and autonomous exploitationPACEbench v2.0 (test)59A-CVE Success Rate10