AI BENCHY 分类
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 ↓.
189/189
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） |
|---|---|---|---|---|---|---|---|
| #156 | Grok 4.20 Multi Agent Beta medium | X AI | 3.3 | 5.0 | $5.599 | 1/1 | 27.1s |
| #12 | GPT-5.5 medium | OpenAI | 8.8 | 9.0 | $3.679 | 2/3 | 59.8s |
| #9 | Claude Fable 5 medium | Anthropic | 10.0 | 9.2 | $3.165 | 3/3 | 15.6s |
| #111 | Gemini 3.1 Flash Lite Preview high | 0.0 | 6.1 | $2.310 | 0/0 | 0ms | |
| #49 | Claude Opus 4.6 medium | Anthropic | 5.7 | 7.7 | $2.053 | 1/3 | 30.1s |
| #97 | Gemini 3.1 Flash Lite high | 3.3 | 6.5 | $2.044 | 1/1 | 137.6s | |
| #26 | Grok 4.5 medium | X AI | 7.6 | 8.3 | $1.696 | 2/3 | 155.7s |
| #39 | Claude Sonnet 4.6 medium | Anthropic | 5.7 | 7.8 | $1.418 | 1/3 | 33.3s |
| #46 | Claude Opus 4.8 low | Anthropic | 6.6 | 7.7 | $1.270 | 1/3 | 7.58s |
| #20 | GPT-5.4 medium | OpenAI | 8.8 | 8.5 | $1.210 | 2/3 | 44.4s |
| #76 | Step 3.7 Flash high | Stepfun | 4.0 | 7.1 | $1.148 | 0/3 | 206.2s |
| #1 | Gemini 3.5 Flash high | 10.0 | 9.8 | $1.115 | 3/3 | 23.0s | |
| #15 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.8 | $1.107 | 3/3 | 15.3s |
| #80 | Gemini 3.5 Flash none | 8.8 | 7.0 | $1.079 | 2/3 | 34.7s | |
| #10 | Gemini 3.1 Pro Preview medium | 7.9 | 9.2 | $1.054 | 2/3 | 40.2s |