CWE-bench
CWE-bench results reported for 9 models across 1 version. Updated 2026-10-07.
Report an issueVersions
1 version, plus 3 variants and configurations · Metric: CWE-bench Programmatic Pass@1
| Version | Released | Models | Results | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CWE-bench 1Latest3 variants of 1
| September 25, 2026 | 1 | 1 |
Recently reported results: CWE-bench 1
Latest version: CWE-bench 1
| Model | Score | Source |
|---|---|---|
| Gemini 4 Argon (highest thinking settings) | 68.0% | deepmind.google for Gemini 4 Argon (highest thinking settings) on CWE-bench 1 (opens in a new tab)CWE-bench Programmatic Pass@1Reported Evaluation methodologyGoogle DeepMindSelf-reportedCollinear AIRecord for Gemini 4 Argon on CWE-bench 1 |