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: 测试正确 ↑.
| 排名 | 模型 | 公司 | 编程 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #93 | Step 3.5 Flash none | Stepfun | 3.0 | 3.0 | 0/1 | 0ms |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 10.0 | 1/1 | 79.7s | |
| #2 | Gemini 3.1 Pro Preview medium | 10.0 | 9.6 | 1/1 | 19.9s | |
| #3 | Gemini 3 Flash Preview low | 10.0 | 8.8 | 1/1 | 6.94s | |
| #4 | Seed-2.0-Lite medium | Bytedance Seed | 10.0 | 8.6 | 1/1 | 74.5s |
| #5 | GPT-5.3-Codex medium | OpenAI | 10.0 | 8.6 | 1/1 | 8.95s |
| #6 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 8.5 | 1/1 | 120.9s |
| #8 | Qwen3.5-27B medium | Qwen | 10.0 | 8.4 | 1/1 | 70.4s |
| #11 | GLM 5 medium | Z.ai | 10.0 | 8.4 | 1/1 | 79.1s |
| #13 | Gemini 2.5 Flash medium | 10.0 | 8.2 | 1/1 | 16.2s | |
| #14 | GPT-5.4 medium | OpenAI | 10.0 | 8.2 | 1/1 | 13.0s |
| #15 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 8.2 | 1/1 | 4.34s | |
| #16 | GLM 5 Turbo medium | Z.ai | 10.0 | 8.1 | 1/1 | 12.3s |
| #19 | Gemini 3 Flash Preview none | 10.0 | 8.1 | 1/1 | 1.59s | |
| #20 | Gemini 3.1 Flash Lite Preview low | 10.0 | 8.1 | 1/1 | 2.20s |