ResearchDatasetsCVE-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCybersecurity vulnerability remediationCVE-Bench (one-day)29Pass@15Automated Vulnerability ExploitationCVE-Bench zero-day vulnerabilities (test)25Success@15Cybersecurity vulnerability remediationCVE-Bench25Pass@12Cybersecurity vulnerability remediationCVE-Bench 1.090Pass@1 Rate1Cybersecurity vulnerability remediationCVE-Bench (zero-day)8Pass@11