CWE-bench v1
Vulnerability patching (programmatic pass@1, v1).
- Category
- Coding
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- All model rankings (records) · Ranked results: 2
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 2)
official results (Gemini 4 Carbon (Google DeepMind models page, benchmark table))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | High | 71.0% | — | Collinear AI / Artificial Analysis | Gemini 4 Carbon (Google DeepMind models page, benchmark table)Retrieved 2026-11-12 · Vendor-reported value. Google published table. methodology PDF: Gemini 4 Carbon/Argon used the highest Gemini API thinking setting, pass@1, and a single trial. Row-specific source: official leaderboard (independent evaluation by Collinear AI / Artificial Analysis), programmatic pass@1Source excerptCWE-bench v1: Gemini 4 Carbon 71.0 |
| 2 | Gemini 4 Argon | High | 68.0% | — | Collinear AI / Artificial Analysis | Gemini 4 Carbon (Google DeepMind models page, benchmark table)Retrieved 2026-11-12 · Vendor-reported value. Google published table. methodology PDF: Gemini 4 Carbon/Argon used the highest Gemini API thinking setting, pass@1, and a single trial. Row-specific source: official leaderboard (independent evaluation by Collinear AI / Artificial Analysis), programmatic pass@1Source excerptCWE-bench v1: Gemini 4 Argon 68.0 |