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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #109 | Nemotron 3 Ultra medium | NVIDIA | 0.5 | 0.8 | $0.674 | 1/3 | 3.54s |
| #126 | Step 3.7 Flash medium | Stepfun | 0.6 | 0.8 | $0.571 | 1/3 | 6.19s |
| #131 | Muse Wonder high | Meta | 0.5 | 0.8 | $3.426 | 1/3 | 3.78s |
| #133 | Muse Glimmer 30B high | Meta | 0.6 | 0.8 | $0.506 | 1/3 | 64.8s |
| #137 | Qwen3.7 Flash low | Qwen | 0.7 | 0.8 | $0.071 | 1/3 | 9.79s |
| #138 | Muse Glimmer 30B medium | Meta | 0.6 | 0.8 | $0.288 | 1/3 | 64.7s |
| #139 | Muse Wonder xhigh | Meta | 0.5 | 0.8 | $4.012 | 1/3 | 3.53s |
| #146 | Mistral Large 4 high | Mistral | 0.5 | 0.8 | $1.391 | 1/3 | 55.2s |
| #165 | Qwen3.5-27B none | Qwen | 0.7 | 0.7 | $0.116 | 1/3 | 1.38s |
| #170 | Qwen3.7 Flash high | Qwen | 0.7 | 0.7 | $0.063 | 1/3 | 10.8s |
| #171 | LongCat 2.0 medium | Meituan | 0.5 | 0.7 | $0.767 | 1/3 | 8.84s |
| #173 | Step 3.7 Flash low | Stepfun | 0.6 | 0.7 | $0.449 | 1/3 | 1.84s |
| #183 | Kimi K2.7 Code medium | Moonshot AI | 0.6 | 0.7 | $1.136 | 1/3 | 41.0s |
| #185 | Step 5 Preview high | Stepfun | 0.6 | 0.7 | $4.513 | 1/3 | 143.2s |
| #196 | Kimi K2.6 medium | Moonshot AI | 0.6 | 0.7 | $1.594 | 1/3 | 25.1s |