CWE-bench v1: Security Logging and Alerting Failures
Code · 2026-09-25
Programmatic pass@1 on the OWASP 2025 A09 subset of CWE-bench v1; exact category denominator is not published.
Top models (higher is better)
| Model | Score |
|---|---|
| Grok 4.7 | 75.0 |
| Gemini 4 Argon | 70.0 |
| Claude Opus 5.5 | 65.0 |
| GPT-6 Astra | 65.0 |
| Muse Spark 1.3 | 63.0 |
| Hy4 Preview | 58.0 |
| DeepSeek V4.1 Flash | 55.0 |
| Claude Fable 5.1 | 53.0 |
| GPT-6 Sol | 53.0 |
| Grok 4.6 | 50.0 |
| Inkling | 33.0 |