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: 指标 ↑.
289/289
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） |
|---|---|---|---|---|---|---|---|
| #213 | Nemotron 3.5 Lightning high | NVIDIA | 4.4 | 5.6 | $0.134 | 0/3 | 168.4s |
| #234 | Nemotron 3.5 Lightning medium | NVIDIA | 4.4 | 5.1 | $0.156 | 0/3 | 285.5s |
| #236 | Mistral Small 4 medium | Mistral | 4.4 | 5.1 | $0.097 | 0/3 | 40.0s |
| #233 | Inkling none | Thinkingmachines | 4.5 | 5.2 | $0.142 | 0/3 | 1.01s |
| #276 | Granite 4.1 8B none | IBM Granite | 4.5 | 4.0 | $0.007 | 0/3 | 775ms |
| #197 | North Mini Code medium | Cohere | 4.5 | 5.7 | $0.000 | 0/3 | 320.4s |
| #194 | Seed 2.1 Turbo none | Bytedance Seed | 4.5 | 5.9 | $0.092 | 0/3 | 2.35s |
| #168 | Claude Sonnet 5 none | Anthropic | 4.6 | 6.1 | $0.548 | 0/3 | 3.67s |
| #232 | Dots 3 Note Preview none | Dots Studio | 4.6 | 5.2 | $0.000 | 0/3 | 6.12s |
| #237 | Qwen3 Coder Next none | Qwen | 4.6 | 5.1 | $0.026 | 0/3 | 2.22s |
| #200 | Inkling Small low | Thinkingmachines | 4.6 | 5.7 | $0.055 | 0/3 | 3.70s |
| #251 | GPT-5.4 Nano none | OpenAI | 4.6 | 4.8 | $0.041 | 0/3 | 2.22s |
| #118 | GLM 5.1 medium | Z.ai | 4.6 | 7.0 | $0.727 | 0/3 | 109.6s |
| #128 | Qwen3.6 Flash medium | Qwen | 5.0 | 6.8 | $0.741 | 0/3 | 42.9s |
| #175 | Inkling low | Thinkingmachines | 5.1 | 6.1 | $0.181 | 0/3 | 8.71s |