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） |
|---|---|---|---|---|---|---|---|
| #5 | GPT-5.6 Sol medium | OpenAI | 10.0 | 9.4 | $0.966 | 3/3 | 9.40s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 8.8 | 8.9 | $0.960 | 2/3 | 146.5s |
| #54 | Grok Build 0.1 medium | X AI | 5.7 | 7.6 | $0.927 | 1/3 | 108.5s |
| #51 | GPT-5.6 Luna high | OpenAI | 5.5 | 7.7 | $0.924 | 1/3 | 15.6s |
| #7 | GPT-5.5 low | OpenAI | 10.0 | 9.3 | $0.907 | 3/3 | 15.0s |
| #44 | Kimi K2.6 medium | Moonshot AI | 5.7 | 7.8 | $0.888 | 1/3 | 214.4s |
| #29 | GPT-5.6 Terra high | OpenAI | 7.6 | 8.2 | $0.852 | 2/3 | 9.14s |
| #6 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $0.821 | 3/3 | 12.5s |
| #40 | Grok 4.5 low | X AI | 10.0 | 7.8 | $0.760 | 3/3 | 13.7s |
| #83 | Grok 4.20 Beta medium | X AI | 3.3 | 6.8 | $0.750 | 1/1 | 31.4s |
| #13 | GPT-5.3-Codex medium | OpenAI | 10.0 | 8.9 | $0.740 | 3/3 | 19.5s |
| #87 | Mimo V2 Omni medium | Xiaomi | 3.3 | 6.8 | $0.683 | 0/3 | 183.9s |
| #16 | Claude Opus 4.7 medium | Anthropic | 7.6 | 8.7 | $0.679 | 2/3 | 13.0s |
| #2 | Gemini 3 Flash Preview medium | 8.6 | 9.6 | $0.667 | 2/3 | 84.4s | |
| #3 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.5 | $0.649 | 3/3 | 11.3s |