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） |
|---|---|---|---|---|---|---|---|
| #141 | GLM 5 Turbo none | Z.ai | 3.9 | 5.3 | $0.047 | 0/3 | 2.41s |
| #143 | GPT-5.6 Luna none | OpenAI | 3.8 | 5.3 | $0.047 | 0/3 | 980ms |
| #126 | Mimo V2 PRO none | Xiaomi | 5.5 | 5.8 | $0.045 | 1/3 | 2.65s |
| #72 | Gemma 4 26B A4B medium | 2.9 | 7.2 | $0.045 | 0/3 | 272.5s | |
| #63 | Seed-2.0-Mini medium | Bytedance Seed | 5.5 | 7.4 | $0.044 | 1/3 | 220.5s |
| #75 | MiMo-V2-Flash medium | Xiaomi | 6.0 | 7.1 | $0.043 | 1/3 | 10.7s |
| #74 | GLM 5.2 none | Z.ai | 3.7 | 7.1 | $0.042 | 0/3 | 7.55s |
| #61 | DeepSeek V3.2 medium | DeepSeek | 6.0 | 7.5 | $0.042 | 1/3 | 248.7s |
| #144 | GPT-5.4 Mini none | OpenAI | 5.5 | 5.3 | $0.038 | 1/3 | 913ms |
| #185 | Qwen3.5-9B medium | Qwen | 2.9 | 3.8 | $0.036 | 0/3 | 100.9s |
| #78 | Laguna XS 2.1 medium | Poolside | 5.5 | 7.0 | $0.036 | 1/3 | 70.3s |
| #71 | DeepSeek V4 Pro none | DeepSeek | 5.6 | 7.2 | $0.034 | 1/3 | 13.4s |
| #86 | Ring-2.6-1T medium | Inclusionai | 5.3 | 6.8 | $0.033 | 1/3 | 59.6s |
| #103 | Gemma 4 31B medium | 4.3 | 6.3 | $0.033 | 0/3 | 219.8s | |
| #158 | Laguna M.1 medium | Poolside | 1.5 | 5.0 | $0.033 | 0/1 | 35.6s |