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） |
|---|---|---|---|---|---|---|---|
| #31 | Claude Sonnet 5.5 max | Anthropic | 1.0 | 0.9 | $8.557 | 3/3 | 55.3s |
| #8 | GPT-6 Astra xhigh | OpenAI | 1.0 | 1.0 | $6.213 | 3/3 | 8.27s |
| #369 | Grok 4.20 Multi Agent Beta medium | X AI | 0.3 | 0.4 | $5.599 | 1/1 | 27.1s |
| #49 | Claude Fable 5 medium | Anthropic | 1.0 | 0.9 | $5.089 | 3/3 | 15.6s |
| #5 | GPT-6 Astra max | OpenAI | 1.0 | 1.0 | $5.044 | 3/3 | 14.6s |
| #30 | GPT-5.5 medium | OpenAI | 0.9 | 0.9 | $4.809 | 2/3 | 59.8s |
| #78 | GLM 5.2 high | Z.ai | 0.6 | 0.8 | $4.632 | 1/3 | 73.0s |
| #26 | Claude Opus 5 high | Anthropic | 1.0 | 0.9 | $4.524 | 3/3 | 12.7s |
| #169 | Step 5 Preview high | Stepfun | 0.3 | 0.7 | $4.513 | 0/3 | 421.7s |
| #7 | GPT-6 Astra high | OpenAI | 1.0 | 1.0 | $4.458 | 3/3 | 5.86s |
| #250 | Step 5 Preview medium | Stepfun | 0.3 | 0.6 | $4.136 | 0/3 | 363.9s |
| #281 | Step 5 Preview low | Stepfun | 0.3 | 0.6 | $4.110 | 0/3 | 378.2s |
| #71 | Qwen3.8 2.4T A95B low | Qwen | 0.8 | 0.8 | $4.016 | 2/3 | 172.5s |
| #153 | Claude Opus 4.8 low | Anthropic | 0.7 | 0.7 | $3.787 | 1/3 | 7.58s |
| #93 | Claude Opus 4.7 medium | Anthropic | 0.8 | 0.8 | $3.636 | 2/3 | 13.0s |