谜题求解 排名
看看哪些 AI 模型在 谜题求解 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 ↑.
216/216
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 | 谜题求解 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #94 | Qwen3.6 35B A3B medium | Qwen | 8.0 | 6.7 | $0.746 | 2/3 | 5.95s |
| #62 | Qwen3.5-27B medium | Qwen | 8.2 | 7.4 | $1.627 | 2/3 | 59.6s |
| #5 | GPT-5.6 Sol low | OpenAI | 8.2 | 9.5 | $0.971 | 2/3 | 3.44s |
| #7 | GPT-5.6 Sol medium | OpenAI | 8.2 | 9.4 | $1.316 | 2/3 | 2.98s |
| #21 | GPT-5.4 medium | OpenAI | 8.2 | 8.5 | $1.533 | 2/3 | 9.14s |
| #31 | Gemini 3.5 Flash-Lite high | 8.2 | 8.1 | $0.584 | 2/3 | 1.85s | |
| #42 | GLM 5.2 medium | Z.ai | 8.2 | 7.8 | $0.187 | 2/3 | 13.1s |
| #49 | DeepSeek V4 Flash high | DeepSeek | 8.2 | 7.7 | $0.041 | 2/3 | 26.1s |
| #73 | KAT-Coder-Pro V2.5 high | Kwaipilot | 8.2 | 7.2 | $0.482 | 2/3 | 3.38s |
| #74 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 8.2 | 7.2 | $0.317 | 2/3 | 17.7s |
| #78 | GLM 5.1 medium | Z.ai | 8.2 | 7.1 | $0.535 | 2/3 | 31.6s |
| #84 | Seed-2.0-Mini medium | Bytedance Seed | 8.2 | 7.0 | $0.101 | 2/3 | 31.8s |
| #89 | Qwen3.6 Flash medium | Qwen | 8.2 | 6.9 | $0.738 | 2/3 | 6.29s |
| #97 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.2 | 6.7 | $0.476 | 2/3 | 3.03s |
| #107 | MiMo-V2.5 medium | Xiaomi | 8.2 | 6.5 | $0.082 | 2/3 | 20.3s |