CWE-bench v2 makes cyber-agent testing public and reproducible
Cybersecurity model builders can now run a public, no-extra-cost benchmark of 100 tasks that ask an agent to find and fix weaknesses in real open-source repositories without breaking them. The set spans 91 CWE vulnerability classes, and its programmatic graders produce deterministic results anyone can reproduce. In the reported comparison, Gemini 4 Argon leads at 67.8% pass@1, but still fails 19% of tasks on every attempt, leaving the long tail unsolved.