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。
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） |
|---|---|---|---|---|---|---|---|
| #24 | GLM 5 Turbo medium | Z.ai | 8.2 | 8.4 | $0.323 | 2/3 | 45.9s |
| #57 | Mercury 2 medium | Inception | 8.2 | 7.5 | $0.058 | 2/3 | 2.04s |
| #21 | Seed-2.0-Lite medium | Bytedance Seed | 8.0 | 8.5 | $0.175 | 2/3 | 156.7s |
| #10 | Gemini 3.1 Pro Preview medium | 7.9 | 9.2 | $1.054 | 2/3 | 40.2s | |
| #11 | Gemini 3.5 Flash medium | 7.9 | 9.1 | $0.582 | 2/3 | 12.6s | |
| #8 | Gemini 3.5 Flash low | 7.8 | 9.2 | $0.349 | 2/3 | 6.71s | |
| #27 | DeepSeek V4 Flash high | DeepSeek | 7.8 | 8.3 | $0.027 | 2/3 | 50.6s |
| #133 | Grok 4.1 Fast medium | X AI | 7.8 | 5.6 | $0.069 | 0/1 | 23.6s |
| #28 | Gemini 2.5 Flash medium | 7.8 | 8.2 | $0.379 | 2/3 | 41.0s | |
| #89 | Qwen3.6 35B A3B medium | Qwen | 7.7 | 6.7 | $0.146 | 2/3 | 50.5s |
| #95 | Qwen3.6 27B medium | Qwen | 7.7 | 6.6 | $0.336 | 2/3 | 143.0s |
| #16 | Claude Opus 4.7 medium | Anthropic | 7.6 | 8.7 | $0.679 | 2/3 | 13.0s |
| #26 | Grok 4.5 medium | X AI | 7.6 | 8.3 | $1.696 | 2/3 | 155.7s |
| #29 | GPT-5.6 Terra high | OpenAI | 7.6 | 8.2 | $0.852 | 2/3 | 9.14s |
| #79 | Kimi K2.7 Code medium | Moonshot AI | 7.6 | 7.0 | $0.581 | 2/3 | 146.7s |