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 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #146 | LongCat 2.0 high | Meituan | 0.8 | 0.7 | $0.778 | 2/3 | 505.3s |
| #148 | Gemini 3.5 Flash Lite medium | 0.8 | 0.7 | $0.440 | 2/3 | 9.96s | |
| #154 | Qwen3.7 Flash high | Qwen | 0.8 | 0.7 | $0.063 | 2/3 | 58.8s |
| #157 | Step 3.7 Flash low | Stepfun | 0.8 | 0.7 | $0.449 | 2/3 | 9.46s |
| #158 | Qwen3.6 27B medium | Qwen | 0.8 | 0.7 | $1.021 | 2/3 | 143.0s |
| #160 | Qwen3.8 Flash Next xhigh | Qwen | 0.7 | 0.7 | ~$0.195 | 2/3 | 192.2s |
| #162 | MiMo-V2.6-Flash low | Xiaomi | 0.8 | 0.7 | $0.200 | 2/3 | 11.0s |
| #164 | GPT-5.2 Chat default | OpenAI | 0.9 | 0.7 | $0.594 | 2/3 | 9.82s |
| #165 | Qwen3.6 Max Preview medium | Qwen | 0.9 | 0.7 | $1.132 | 2/3 | 146.5s |
| #167 | Kimi K2.7 Code medium | Moonshot AI | 0.8 | 0.7 | $1.136 | 2/3 | 146.7s |
| #173 | Muse Glimmer 30B low | Meta | 0.8 | 0.7 | $0.219 | 2/3 | 16.5s |
| #175 | Ember-1 high | Fireworks | 0.8 | 0.7 | $2.405 | 2/3 | 72.2s |
| #183 | Mercury 2.5 Preview medium | Inception | 0.8 | 0.7 | $0.039 | 2/3 | 3.86s |
| #202 | Mercury 2 medium | Inception | 0.8 | 0.7 | $0.121 | 2/3 | 2.04s |
| #204 | KAT-Coder-Pro V2.5 low | Kwaipilot | 0.8 | 0.7 | $0.568 | 2/3 | 24.9s |