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: 总成本 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #215 | Hy3 preview low | Tencent | 5.3 | 5.5 | $0.042 | 1/3 | 27.9s |
| #76 | DeepSeek V4 Flash 0423 high | DeepSeek | 7.8 | 7.6 | $0.042 | 2/3 | 50.6s |
| #251 | GPT-5.4 Nano none | OpenAI | 4.6 | 4.8 | $0.041 | 0/3 | 2.22s |
| #218 | DeepSeek V4 Flash 0423 none | DeepSeek | 4.2 | 5.4 | $0.040 | 0/3 | 17.1s |
| #262 | Qwen3 Coder Next medium | Qwen | 3.7 | 4.6 | $0.034 | 0/3 | 924ms |
| #259 | Laguna M.1 medium | Poolside | 1.5 | 4.7 | $0.033 | 0/1 | 35.6s |
| #261 | Mercury 2 none | Inception | 3.4 | 4.7 | $0.030 | 0/3 | 1.03s |
| #221 | GPT-5.6 Luna none | OpenAI | 3.8 | 5.4 | $0.029 | 0/3 | 980ms |
| #199 | GLM 5 none | Z.ai | 4.0 | 5.7 | $0.027 | 0/3 | 5.12s |
| #249 | Ring-2.6-1T none | Inclusionai | 5.3 | 4.8 | $0.026 | 1/3 | 143.8s |
| #237 | Qwen3 Coder Next none | Qwen | 4.6 | 5.1 | $0.026 | 0/3 | 2.22s |
| #238 | MiMo-V2.5 none | Xiaomi | 5.5 | 5.1 | $0.025 | 1/3 | 3.24s |
| #274 | MiMo-V2-Flash none | Xiaomi | 4.3 | 4.0 | $0.025 | 0/3 | 2.64s |
| #264 | Laguna S 2.1 none | Poolside | 3.4 | 4.5 | $0.022 | 0/3 | 550ms |
| #235 | Mistral Small 4 none | Mistral | 3.7 | 5.1 | $0.022 | 0/3 | 901ms |