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 ↓.
408/408
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） |
|---|---|---|---|---|---|---|---|
| #254 | Claude Sonnet 4.6 none | Anthropic | 0.5 | 0.6 | $0.661 | 1/3 | 5.19s |
| #201 | LongCat 2.0 low | Meituan | 0.7 | 0.7 | $0.630 | 1/3 | 479.3s |
| #42 | Gemini 3.5 Flash Lite high | 0.8 | 0.9 | $0.624 | 2/3 | 16.6s | |
| #103 | GLM 5.3 FlashX max | Z.ai | 0.8 | 0.8 | $0.623 | 2/3 | 24.6s |
| #52 | DeepSeek V4.1 Flash high | DeepSeek | 1.0 | 0.9 | $0.617 | 3/3 | 49.2s |
| #164 | GPT-5.2 Chat default | OpenAI | 0.9 | 0.7 | $0.594 | 2/3 | 9.82s |
| #53 | DeepSeek V4.1 Flash medium | DeepSeek | 1.0 | 0.9 | $0.591 | 3/3 | 34.4s |
| #57 | MiMo-V2.6-Pro medium | Xiaomi | 0.8 | 0.9 | $0.586 | 2/3 | 150.4s |
| #73 | Muse Glimmer 30B xhigh | Meta | 1.0 | 0.8 | $0.585 | 3/3 | 105.9s |
| #10 | Gemini 3.6 Flash medium | 1.0 | 1.0 | $0.577 | 3/3 | 14.8s | |
| #77 | DeepSeek V4 Flash 0731 high | DeepSeek | 0.6 | 0.8 | $0.576 | 1/3 | 252.7s |
| #113 | Step 3.7 Flash medium | Stepfun | 0.9 | 0.8 | $0.571 | 2/3 | 27.4s |
| #204 | KAT-Coder-Pro V2.5 low | Kwaipilot | 0.8 | 0.7 | $0.568 | 2/3 | 24.9s |
| #150 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 0.7 | 0.7 | $0.567 | 1/3 | 180.7s |
| #147 | Qwen3.6 Plus medium | Qwen | 0.6 | 0.7 | $0.554 | 1/3 | 153.1s |