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: 响应时间（平均） ↓.
408/408
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） |
|---|---|---|---|---|---|---|---|
| #235 | DeepSeek V3.2 medium | DeepSeek | 0.6 | 0.6 | $0.152 | 1/3 | 248.7s |
| #56 | Qwen3.8 27B high | Qwen | 0.8 | 0.9 | ~$0.298 | 2/3 | 248.6s |
| #271 | Trinity Large Thinking high | Arcee AI | 0.4 | 0.6 | $0.794 | 0/3 | 245.0s |
| #230 | Solar Pro 4 high | Upstage | 0.6 | 0.6 | $0.077 | 1/3 | 244.7s |
| #92 | DeepSeek V4 Pro 0423 high | DeepSeek | 0.6 | 0.8 | $0.149 | 1/3 | 243.0s |
| #347 | Nemotron 3.5 Lightning low | NVIDIA | 0.4 | 0.5 | $0.175 | 0/3 | 224.4s |
| #129 | Seed-2.0-Mini medium | Bytedance Seed | 0.6 | 0.8 | $0.140 | 1/3 | 220.5s |
| #176 | Gemma 4 31B medium | 0.4 | 0.7 | $0.144 | 0/3 | 219.8s | |
| #295 | Hy4 preview low | Tencent | 0.5 | 0.5 | $1.844 | 0/3 | 219.1s |
| #218 | Kimi K2.5 medium | Moonshot AI | 0.6 | 0.6 | $0.841 | 1/3 | 217.5s |
| #180 | Kimi K2.6 medium | Moonshot AI | 0.6 | 0.7 | $1.594 | 1/3 | 214.4s |
| #378 | Ling 3.0 Tiny medium | Inclusionai | 0.3 | 0.4 | $0.000 | 0/3 | 212.0s |
| #225 | Qwen3.5-35B-A3B medium | Qwen | 0.6 | 0.6 | $0.716 | 1/3 | 206.6s |
| #203 | Step 3.7 Flash high | Stepfun | 0.4 | 0.7 | $1.478 | 0/3 | 206.2s |
| #117 | DeepSeek V4 Flash 0731 medium | DeepSeek | 0.6 | 0.8 | $0.460 | 1/3 | 198.8s |