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。
| 排名 | 模型 | 公司 | 编程 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #2 | Gemini 3.5 Flash high | 10.0 | 9.6 | 2/2 | 24.6s | |
| #5 | Qwen3.7 Max medium | Qwen | 10.0 | 9.0 | 2/2 | 23.0s |
| #7 | Claude Opus 4.7 medium | Anthropic | 10.0 | 8.9 | 2/2 | 14.8s |
| #8 | GPT-5.5 low | OpenAI | 10.0 | 8.9 | 2/2 | 14.4s |
| #10 | Claude Opus 4.7 none | Anthropic | 10.0 | 8.9 | 1/1 | 2.84s |
| #14 | Grok 4.20 Beta medium | X AI | 10.0 | 8.5 | 1/1 | 31.4s |
| #16 | GPT-5.3-Codex medium | OpenAI | 10.0 | 8.3 | 2/2 | 18.5s |
| #18 | GLM 5 medium | Z.ai | 10.0 | 8.2 | 2/2 | 89.5s |
| #19 | Hy3 preview medium | Tencent | 10.0 | 8.1 | 1/1 | 31.4s |
| #22 | Hy3 preview high | Tencent | 10.0 | 8.1 | 1/1 | 99.8s |
| #39 | Hy3 preview low | Tencent | 10.0 | 7.7 | 1/1 | 27.9s |
| #51 | Gemini 3.1 Flash Lite high | 10.0 | 7.5 | 1/1 | 137.6s | |
| #60 | GPT-5.2 medium | OpenAI | 10.0 | 7.3 | 2/2 | 23.2s |
| #64 | Ring-2.6-1T medium | Inclusionai | 10.0 | 7.2 | 1/1 | 59.6s |
| #65 | Ring-2.6-1T none | Inclusionai | 10.0 | 7.2 | 1/1 | 143.8s |