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） |
|---|---|---|---|---|---|---|---|
| #157 | Trinity Large Preview none | Arcee AI | 3.7 | 5.0 | $0.008 | 0/3 | 14.3s |
| #168 | Qwen3 Coder Next medium | Qwen | 3.7 | 4.7 | $0.008 | 0/3 | 924ms |
| #150 | Qwen3 Coder Next none | Qwen | 4.6 | 5.1 | $0.009 | 0/3 | 2.22s |
| #170 | Laguna M.1 none | Poolside | 2.5 | 4.6 | $0.009 | 0/1 | 2.93s |
| #184 | gpt-oss-120b none | OpenAI | 1.5 | 4.0 | $0.010 | 0/1 | 9.57s |
| #165 | GPT-5.4 Nano none | OpenAI | 4.6 | 4.8 | $0.011 | 0/3 | 2.22s |
| #171 | Mercury 2 none | Inception | 3.4 | 4.6 | $0.011 | 0/3 | 1.03s |
| #120 | Qwen3.5-35B-A3B none | Qwen | 5.5 | 5.9 | $0.012 | 1/3 | 1.39s |
| #92 | gpt-oss-120b medium | OpenAI | 5.9 | 6.7 | $0.013 | 1/3 | 38.4s |
| #112 | Gemini 3.1 Flash Lite none | 5.5 | 6.1 | $0.013 | 1/3 | 938ms | |
| #110 | Gemini 3.1 Flash Lite minimal | 5.5 | 6.1 | $0.013 | 1/3 | 831ms | |
| #119 | Qwen3.6 Flash none | Qwen | 5.4 | 6.0 | $0.015 | 1/3 | 1.79s |
| #121 | Qwen3.5-27B none | Qwen | 5.8 | 5.9 | $0.015 | 1/3 | 1.80s |
| #100 | Hy3 preview low | Tencent | 5.3 | 6.4 | $0.015 | 1/3 | 27.9s |
| #176 | Laguna Xs.2 medium | Poolside | 2.1 | 4.3 | $0.015 | 0/1 | 14.4s |