HyperAI
Command Palette
Search for a command to run...
CyberGym-E2E-AA
Berkeley RDI CyberGym-E2E 的实现，这是一个防御性网络安全基准，测试智能体能否在 C/C++ 开源项目中找到真实的内存安全漏洞、用概念验证输入复现，并在不破坏项目测试的前提下完成修补。
- 模型
- 19 当前，25 总共
- 中位数
- 71.8%
- 范围
- 0.0%–94.7%
| 排名 | 比较 | 模型 | 评分 |
|---|---|---|---|
| 1 |  Kimi K3.1 Pro Kimi | 94.7% | |
| 2 | 93.1% | ||
| 3 |  Mistral Large 4 (High) Mistral | 79.4% | |
| 4 |  MiMo-V2.6-Pro Xiaomi | 78.6% | |
| 5 |  GPT-6 Luna (Max) OpenAI | 77.9% | |
| 6 |  DeepSeek V4.1 Flash 1017 (Max) DeepSeek | 76.3% | |
| 7 |  Step 5 Preview StepFun | 74.8% | |
| 8 |  GLM-5.3-Flash Z AI | 74.0% | |
| 9 |  Grok 4.7 (Xhigh) SpaceXAI | 74.0% | |
| 10 | Mistral Large 4 (Medium) Mistral | 71.8% | |
| 11 |  Beam 1.0 Reflection | 45.0% | |
| 12 | GLM-5.3 (Max) Z AI | 29.0% | |
| 13 |  MiniMax-M3 MiniMax | 24.4% | |
| 14 | 10.7% | ||
| 15 |  Gemini 3.8 Flash (High) Google | 8.4% | |
| 16 | 0.8% | ||
| 17 | GPT-6 Astra (Max) OpenAI | 0.0% | |
| 18 |  Qwen3.8 2.4T A95B Alibaba | 0.0% | |
| 19 | Qwen3.8 27B (Xhigh) Alibaba | 0.0% |
