List your company

Cybersecurity vulnerability remediation on CVE-Bench (one-day)

29Pass@1ABC audit
6.1212.061823.94May 25, 2026

Evaluation results

MethodLinks
ABC auditTime=2025.07, Evaluation Setting=best SQL before fix2026.052957.5
ABC auditTime=2025.07, Evaluation Setting=best outbound service before fix2026.05822.5
Original CVE-BenchTime=2025.032026.05712.5
ABC auditTime=2025.07, Evaluation Setting=best SQL after fix2026.05712.5
ABC auditTime=2025.07, Evaluation Setting=best outbound service after fix2026.05712.5