编程 排名
看看哪些 AI 模型在 编程 上表现最好，哪些更稳定，以及差距主要出现在哪里。
226/226
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 编程 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #205 | MiniMax M2.5 medium | Minimax | 3.4 | 4.6 | $0.340 | 0/3 | 188.6s |
| #206 | Laguna S 2.1 none | Poolside | 3.4 | 4.5 | $0.025 | 0/3 | 550ms |
| #204 | Mercury 2 none | Inception | 3.4 | 4.6 | $0.030 | 0/3 | 1.03s |
| #103 | Claude Opus 4.7 none | Anthropic | 3.3 | 6.6 | $0.505 | 1/1 | 2.84s |
| #142 | Grok 4.20 Beta medium | X AI | 3.3 | 6.0 | $0.750 | 1/1 | 31.4s |
| #155 | Gemini 3.1 Flash Lite high | 3.3 | 5.6 | $2.044 | 1/1 | 137.6s | |
| #196 | Grok 4.20 Multi Agent Beta medium | X AI | 3.3 | 4.8 | $5.599 | 1/1 | 27.1s |
| #218 | Grok Build 0.1 none | X AI | 3.3 | 4.0 | $0.547 | 1/1 | 21.4s |
| #224 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.3 | 3.2 | $0.000 | 1/1 | 1.27s |
| #197 | KAT-Coder-Air V2.5 none | Kwaipilot | 3.3 | 4.8 | $0.067 | 0/3 | 14.3s |
| #192 | Nemotron 3 Super none | NVIDIA | 3.3 | 4.9 | $0.008 | 0/3 | 2.64s |
| #145 | Mimo V2 Omni medium | Xiaomi | 3.3 | 5.9 | $0.683 | 0/3 | 183.9s |
| #210 | GLM 4.7 Flash medium | Z.ai | 3.2 | 4.3 | $0.166 | 0/3 | 55.3s |
| #189 | GPT-4o-mini none | OpenAI | 3.2 | 5.0 | $0.010 | 0/3 | 1.63s |
| #151 | Nemotron 3 Super medium | NVIDIA | 3.1 | 5.7 | $0.050 | 0/3 | 147.3s |