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） |
|---|---|---|---|---|---|---|---|
| #139 | DeepSeek V4 Pro 0423 none | DeepSeek | 0.6 | 0.7 | $0.083 | 1/3 | 13.4s |
| #143 | Claude Fable 5.1 medium | Anthropic | 0.7 | 0.7 | $3.197 | 1/3 | 11.0s |
| #144 | Grok 4.7 medium | X AI | 0.7 | 0.7 | $2.938 | 1/3 | 312.2s |
| #147 | Qwen3.6 Plus medium | Qwen | 0.6 | 0.7 | $0.554 | 1/3 | 153.1s |
| #149 | Qwen3.5-27B none | Qwen | 0.6 | 0.7 | $0.116 | 1/3 | 1.80s |
| #150 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 0.7 | 0.7 | $0.567 | 1/3 | 180.7s |
| #152 | Gemini 3.8 Flash low | 0.5 | 0.7 | $0.323 | 1/3 | 4.31s | |
| #153 | Claude Opus 4.8 low | Anthropic | 0.7 | 0.7 | $3.787 | 1/3 | 7.58s |
| #159 | Claude Opus 5 none | Anthropic | 0.6 | 0.7 | $2.766 | 1/3 | 5.54s |
| #161 | GLM 5.3 FlashX medium | Z.ai | 0.6 | 0.7 | $0.114 | 1/3 | 6.37s |
| #163 | MiMo-V2.5 medium | Xiaomi | 0.6 | 0.7 | $0.130 | 1/3 | 97.1s |
| #166 | Gemini 3.1 Flash Lite Preview medium | 0.5 | 0.7 | $0.158 | 1/3 | 4.09s | |
| #170 | Qwen3.5-122B-A10B medium | Qwen | 0.6 | 0.7 | $1.152 | 1/3 | 114.5s |
| #171 | Grok 4.6 low | X AI | 0.6 | 0.7 | $0.781 | 1/3 | 21.7s |
| #172 | Gemini 3 Flash Preview low | 0.6 | 0.7 | $0.254 | 1/3 | 6.00s |