Wiz Cyber Model Arena (Claude Code) - Overall: leaderboard
Wiz Cyber Model Arena scores AI agents on offensive security challenges in four categories (code vulnerabilities, API security, Websec.fr CTFs, cloud security). This board is Overall pass@1, the mean of the four category rates, for models run in the Claude Code harness; higher is better.
Metric: Macro average of the four category pass@1 rates (%). Source: www.wiz.io. Saturation forecast: Around November 2027. 25 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 71.2 | #16 |
| 2 | Gemini 4 Argon | 70.8 | #9 |
| 3 | GPT-6.1 Sol | 70.7 | #7 |
| 4 | GPT-6 Astra | 70.2 | #6 |
| 5 | GPT-6 Sol | 69.3 | #19 |
| 6 | Claude Opus 4.8 | 65.4 | #39 |
| 7 | Claude Opus 5.5 | 64.5 | #3 |
| 8 | GPT-5.6 Terra | 64.4 | #40 |
| 9 | GPT-5.6 Sol | 64.2 | #22 |
| 10 | Gemini 3.5 Flash | 60.5 | #66 |
| 11 | GPT-6 Luna | 60.5 | #61 |
| 12 | DeepSeek V4.1 Flash (1017) | 60.3 | #27 |
| 13 | Claude Sonnet 5 | 59.3 | #65 |
| 14 | Gemini 3.6 Flash | 59.1 | #57 |
| 15 | Gemini 3.7 Flash | 59.1 | #24 |
No result here: #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=wiz-cyber-model-arena-claude-code-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.