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。
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） |
|---|---|---|---|---|---|---|---|
| #53 | DeepSeek V4 Flash 0731 low | DeepSeek | 7.3 | 8.0 | $0.072 | 1/3 | 163.3s |
| #73 | Seed-2.0-Code low | Bytedance Seed | 7.0 | 7.7 | $0.767 | 1/3 | 109.7s |
| #186 | GPT-5 Nano medium | OpenAI | 7.0 | 6.0 | $0.118 | 1/3 | 41.6s |
| #109 | Qwen3.7 Flash low | Qwen | 6.7 | 7.2 | $0.043 | 1/3 | 42.4s |
| #161 | Ling-3.0-flash high | Inclusionai | 6.7 | 6.4 | $0.021 | 1/3 | 14.9s |
| #99 | GLM 5.3 high | Z.ai | 6.6 | 7.3 | $0.403 | 1/3 | 18.9s |
| #70 | Claude Opus 4.8 low | Anthropic | 6.6 | 7.8 | $2.089 | 1/3 | 7.58s |
| #83 | GPT-5.6 Terra low | OpenAI | 6.6 | 7.5 | $0.420 | 1/3 | 9.56s |
| #140 | LongCat 2.0 low | Meituan | 6.6 | 6.7 | $0.412 | 1/3 | 479.3s |
| #86 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 6.6 | 7.5 | $0.459 | 1/3 | 180.7s |
| #103 | DeepSeek V4 Flash 0731 medium | DeepSeek | 6.4 | 7.3 | $0.106 | 1/3 | 198.8s |
| #106 | KAT-Coder-Pro V2.5 high | Kwaipilot | 6.4 | 7.2 | $0.506 | 1/3 | 22.0s |
| #55 | GLM 5.2 high | Z.ai | 6.4 | 8.0 | $1.188 | 1/3 | 73.0s |
| #121 | Grok 4.20 medium | X AI | 6.3 | 7.0 | $0.805 | 1/3 | 109.9s |
| #54 | DeepSeek V4 Flash 0731 high | DeepSeek | 6.3 | 8.0 | $0.134 | 1/3 | 252.7s |