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） |
|---|---|---|---|---|---|---|---|
| #253 | Grok 4.20 Multi Agent Beta medium | X AI | 3.3 | 4.8 | $5.599 | 1/1 | 27.1s |
| #19 | GPT-5.5 medium | OpenAI | 8.8 | 9.0 | $4.163 | 2/3 | 59.8s |
| #58 | Kimi K3 max | Moonshot AI | 10.0 | 7.9 | $3.467 | 3/3 | 325.8s |
| #14 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $3.070 | 3/3 | 12.7s |
| #33 | Claude Fable 5 medium | Anthropic | 10.0 | 8.6 | $3.004 | 3/3 | 15.6s |
| #74 | Claude Opus 4.6 medium | Anthropic | 5.7 | 7.7 | $2.961 | 1/3 | 30.1s |
| #48 | Qwen3.8 2.4T A95B low | Qwen | 7.8 | 8.1 | $2.672 | 2/3 | 172.5s |
| #95 | Qwen3.8 2.4T A95B high | Qwen | 5.9 | 7.4 | $2.357 | 1/3 | 160.5s |
| #230 | Gemini 3.1 Flash Lite Preview high | 0.0 | 5.3 | $2.310 | 0/0 | 0ms | |
| #21 | Grok 4.5 high | X AI | 10.0 | 9.0 | $2.252 | 3/3 | 155.2s |
| #67 | Claude Sonnet 4.6 medium | Anthropic | 5.7 | 7.8 | $2.126 | 1/3 | 33.3s |
| #70 | Claude Opus 4.8 low | Anthropic | 6.6 | 7.8 | $2.089 | 1/3 | 7.58s |
| #205 | Gemini 3.1 Flash Lite high | 3.3 | 5.6 | $2.044 | 1/1 | 137.6s | |
| #37 | Grok 4.5 medium | X AI | 7.6 | 8.5 | $2.042 | 2/3 | 155.7s |
| #6 | Gemini 3.5 Flash high | 10.0 | 9.4 | $2.011 | 3/3 | 23.0s |