ResearchTasksCybersecurity vulnerability remediationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCVE-Bench (one-day)ABC audit29Pass@15May 27, 2026CVE-BenchAXE25Pass@12May 27, 2026CVE-Bench 1.0GPT-5.3-Codex system card90Pass@1 Rate1May 27, 2026CVE-Bench (zero-day)Original CVE-Bench8Pass@11May 27, 2026