HyperAI
Command Palette
Search for a command to run...
CWE-Bench-AA
Collinear AI CWE-bench 的实现，这是一个防御性网络安全基准，测试编程智能体能否审计真实开源代码库，在所述问题范围内发现漏洞，并在不破坏正常行为的前提下完成修补。
- 模型
- 19 当前，25 总共
- 中位数
- 55.8%
- 范围
- 26.7%–69.2%
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 1 |  DeepSeek V4.1 Flash 1017 (Max) DeepSeek | 69.2% | |
| 2 |  Grok 4.7 (Xhigh) SpaceXAI | 68.3% | |
| 3 | 64.7% | ||
| 4 |  GPT-6 Astra (Max) OpenAI | 63.3% | |
| 5 |  MiMo-V2.6-Pro Xiaomi | 63.3% | |
| 6 |  Kimi K3.1 Pro Kimi | 60.8% | |
| 7 | 58.3% | ||
| 8 |  Mistral Large 4 (High) Mistral | 58.3% | |
| 9 | GPT-6 Luna (Max) OpenAI | 56.7% | |
| 10 |  GLM-5.3 (Max) Z AI | 55.8% | |
| 11 | GLM-5.3-Flash Z AI | 55.8% | |
| 12 |  Gemini 3.8 Flash (High) Google | 52.5% | |
| 13 |  Step 5 Preview StepFun | 52.5% | |
| 14 | Mistral Large 4 (Medium) Mistral | 50.0% | |
| 15 |  Beam 1.0 Reflection | 49.2% | |
| 16 |  MiniMax-M3 MiniMax | 41.7% | |
| 17 |  Qwen3.8 2.4T A95B Alibaba | 28.3% | |
| 18 | 27.5% | ||
| 19 | Qwen3.8 27B (Xhigh) Alibaba | 26.7% |
