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。
442/442
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） |
|---|---|---|---|---|---|---|---|
| #366 | Gemini 3.1 Flash Lite high | 0.6 | 0.5 | $2.044 | 1/3 | 50.8s | |
| #126 | Step 3.7 Flash medium | Stepfun | 0.6 | 0.8 | $0.571 | 1/3 | 6.19s |
| #83 | GPT-5 Mini medium | OpenAI | 0.6 | 0.8 | $0.315 | 1/3 | 15.2s |
| #269 | Inkling none | Thinkingmachines | 0.6 | 0.6 | $0.292 | 1/3 | 931ms |
| #300 | GPT-5.4 none | OpenAI | 0.6 | 0.6 | $0.690 | 1/3 | 1.44s |
| #358 | Mercury 2.5 Preview default | Inception | 0.6 | 0.5 | $0.023 | 1/3 | 684ms |
| #70 | DeepSeek V4.1 Flash max | DeepSeek | 0.6 | 0.9 | $1.204 | 1/3 | 30.8s |
| #242 | Dots 3 Note Preview high | Dots Studio | 0.6 | 0.6 | $0.000 | 1/3 | 12.7s |
| #173 | Step 3.7 Flash low | Stepfun | 0.6 | 0.7 | $0.449 | 1/3 | 1.84s |
| #377 | Nemotron 3 Super none | NVIDIA | 0.5 | 0.4 | $0.016 | 1/3 | 2.36s |
| #387 | GLM 5 Turbo none | Z.ai | 0.5 | 0.4 | $0.047 | 1/3 | 2.65s |
| #109 | Nemotron 3 Ultra medium | NVIDIA | 0.5 | 0.8 | $0.674 | 1/3 | 3.54s |
| #146 | Mistral Large 4 high | Mistral | 0.5 | 0.8 | $1.391 | 1/3 | 55.2s |
| #171 | LongCat 2.0 medium | Meituan | 0.5 | 0.7 | $0.767 | 1/3 | 8.84s |
| #218 | Mercury 2 medium | Inception | 0.5 | 0.7 | $0.121 | 1/3 | 949ms |