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） |
|---|---|---|---|---|---|---|---|
| #125 | Qwen3.5-35B-A3B medium | Qwen | 8.2 | 6.2 | $0.837 | 2/3 | 33.1s |
| #141 | Hy3 preview high | Tencent | 7.7 | 5.9 | $0.048 | 2/3 | 27.9s |
| #147 | GLM 5 none | Z.ai | 7.7 | 5.7 | $0.041 | 2/3 | 1.91s |
| #157 | GLM 5.1 none | Z.ai | 7.7 | 5.5 | $0.164 | 2/3 | 1.45s |
| #169 | Gemini 3.1 Flash Lite Preview high | 7.7 | 5.3 | $2.310 | 2/3 | 46.7s | |
| #179 | DeepSeek V3.2 none | DeepSeek | 7.6 | 5.0 | $0.054 | 2/3 | 6.91s |
| #185 | Ring-2.6-1T none | Inclusionai | 7.7 | 4.8 | $0.026 | 2/3 | 31.5s |
| #197 | Grok 4.20 Beta none | X AI | 7.7 | 4.4 | $0.087 | 2/3 | 586ms |
| #1 | Gemini 3.6 Flash medium | 10.0 | 9.9 | $0.831 | 3/3 | 2.53s | |
| #2 | Gemini 3.6 Flash high | 10.0 | 9.7 | $1.785 | 3/3 | 3.04s | |
| #3 | Gemini 3 Flash Preview medium | 10.0 | 9.6 | $0.742 | 3/3 | 4.05s | |
| #4 | Gemini 3.5 Flash high | 10.0 | 9.5 | $1.976 | 3/3 | 3.23s | |
| #6 | Gemini 3.6 Flash low | 10.0 | 9.4 | $0.517 | 3/3 | 1.91s | |
| #8 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $1.234 | 3/3 | 4.10s |
| #9 | GPT-5.5 low | OpenAI | 10.0 | 9.3 | $1.253 | 3/3 | 4.74s |