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。 排序方式: 测试正确 ↑.
289/289
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） |
|---|---|---|---|---|---|---|---|
| #239 | Qwen3.5-9B none | Qwen | 3.9 | 5.1 | $0.021 | 0/3 | 5.60s |
| #240 | GLM 5 Turbo none | Z.ai | 3.9 | 5.1 | $0.047 | 0/3 | 2.41s |
| #241 | North Mini Code none | Cohere | 3.9 | 5.1 | $0.000 | 0/3 | 22.0s |
| #243 | Laguna S 2.1 low | Poolside | 3.8 | 5.0 | $0.082 | 0/3 | 167.5s |
| #244 | DeepSeek V3.2 none | DeepSeek | 3.1 | 5.0 | $0.054 | 0/3 | 14.5s |
| #245 | GPT-4o-mini none | OpenAI | 3.2 | 5.0 | $0.010 | 0/3 | 1.63s |
| #246 | Qwen3.6 Plus Preview medium | Qwen | 9.8 | 4.9 | $0.000 | 0/1 | 0ms |
| #248 | Nemotron 3 Super none | NVIDIA | 3.3 | 4.8 | $0.008 | 0/3 | 2.64s |
| #250 | Nemotron 3.5 Lightning low | NVIDIA | 4.0 | 4.8 | $0.140 | 0/3 | 224.4s |
| #251 | GPT-5.4 Nano none | OpenAI | 4.6 | 4.8 | $0.041 | 0/3 | 2.22s |
| #252 | Trinity Large Thinking high | Arcee AI | 3.7 | 4.8 | $0.624 | 0/3 | 245.0s |
| #254 | KAT-Coder-Air V2.5 none | Kwaipilot | 3.3 | 4.8 | $0.070 | 0/3 | 14.3s |
| #255 | GLM 4.7 Flash none | Z.ai | 4.3 | 4.8 | $0.016 | 0/3 | 2.54s |
| #256 | Trinity Large Preview none | Arcee AI | 3.7 | 4.8 | $0.008 | 0/3 | 14.3s |
| #257 | Hunter Alpha medium | OpenRouter | 9.8 | 4.7 | $0.000 | 0/1 | 0ms |