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: 测试正确 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #74 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 8.2 | 7.2 | $0.317 | 2/3 | 17.7s |
| #75 | Qwen3.7 Plus none | Qwen | 7.7 | 7.2 | $0.106 | 2/3 | 1.71s |
| #78 | GLM 5.1 medium | Z.ai | 8.2 | 7.1 | $0.535 | 2/3 | 31.6s |
| #79 | Grok 4.20 medium | X AI | 7.7 | 7.1 | $0.777 | 2/3 | 6.22s |
| #84 | Seed-2.0-Mini medium | Bytedance Seed | 8.2 | 7.0 | $0.101 | 2/3 | 31.8s |
| #87 | GPT-5.6 Sol none | OpenAI | 7.7 | 6.9 | $0.524 | 2/3 | 1.49s |
| #89 | Qwen3.6 Flash medium | Qwen | 8.2 | 6.9 | $0.738 | 2/3 | 6.29s |
| #91 | GPT-5.5 none | OpenAI | 7.7 | 6.9 | $0.544 | 2/3 | 1.29s |
| #93 | Gemini 3 Flash Preview none | 7.7 | 6.8 | $0.085 | 2/3 | 1.05s | |
| #94 | Qwen3.6 35B A3B medium | Qwen | 8.0 | 6.7 | $0.746 | 2/3 | 5.95s |
| #95 | Gemini 3.5 Flash-Lite low | 7.8 | 6.7 | $0.145 | 2/3 | 1.22s | |
| #97 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.2 | 6.7 | $0.476 | 2/3 | 3.03s |
| #98 | GLM 5V Turbo medium | Z.ai | 7.7 | 6.7 | $0.457 | 2/3 | 10.2s |
| #101 | GLM 5.2 none | Z.ai | 7.7 | 6.6 | $0.128 | 2/3 | 3.31s |
| #104 | Gemini 3.5 Flash-Lite medium | 8.4 | 6.5 | $0.369 | 2/3 | 1.70s |