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） ↓.
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） |
|---|---|---|---|---|---|---|---|
| #228 | Seed-2.0-Code none | Bytedance Seed | 3.6 | 5.3 | $0.151 | 0/3 | 13.4s |
| #133 | DeepSeek V4 Pro none | DeepSeek | 5.6 | 6.8 | $0.351 | 1/3 | 13.4s |
| #29 | Claude Opus 4.7 medium | Anthropic | 7.6 | 8.7 | $1.476 | 2/3 | 13.0s |
| #14 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $3.070 | 3/3 | 12.7s |
| #18 | Gemini 3.5 Flash medium | 7.9 | 9.0 | $0.665 | 2/3 | 12.6s | |
| #9 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $0.629 | 3/3 | 12.5s |
| #4 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.5 | $0.496 | 3/3 | 11.3s |
| #247 | Ling-2.6-flash none | Inclusionai | 5.3 | 4.9 | $0.002 | 1/3 | 11.2s |
| #178 | Gemma 4 31B none | 5.5 | 6.1 | $0.016 | 1/3 | 11.2s | |
| #220 | KAT-Coder-Air V2.5 low | Kwaipilot | 3.5 | 5.4 | $0.046 | 0/3 | 11.1s |
| #164 | MiMo-V2-Flash medium | Xiaomi | 6.0 | 6.3 | $0.043 | 1/3 | 10.7s |
| #229 | Ling-2.6-1T none | Inclusionai | 3.8 | 5.3 | $0.016 | 0/3 | 10.6s |
| #85 | GPT 5.3 Chat none | OpenAI | 5.6 | 7.5 | $0.533 | 1/3 | 10.5s |
| #148 | Inkling Small medium | Thinkingmachines | 7.8 | 6.6 | $0.113 | 2/3 | 10.5s |
| #93 | GPT-5.6 Luna medium | OpenAI | 5.4 | 7.4 | $0.072 | 1/3 | 10.4s |