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: 响应时间（平均） ↑.
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） |
|---|---|---|---|---|---|---|---|
| #133 | Muse Glimmer 30B high | Meta | 0.6 | 0.8 | $0.506 | 1/3 | 64.8s |
| #130 | DeepSeek V4 Flash 0731 medium | DeepSeek | 0.8 | 0.8 | $0.460 | 2/3 | 65.1s |
| #120 | Qwen3.8 2.4T A95B high | Qwen | 1.0 | 0.8 | $2.949 | 3/3 | 65.5s |
| #87 | Muse Spark 1.1 high | Meta | 0.8 | 0.8 | $2.570 | 2/3 | 70.0s |
| #272 | Granite 4.2 8B medium | IBM Granite | 0.3 | 0.6 | $0.029 | 0/3 | 76.0s |
| #414 | Command A+ high | Cohere | 0.3 | 0.3 | $0.079 | 0/3 | 86.2s |
| #417 | Command A+ none | Cohere | 0.3 | 0.3 | $0.000 | 0/3 | 88.1s |
| #323 | Granite 4.2 8B low | IBM Granite | 0.3 | 0.5 | $0.036 | 0/3 | 90.8s |
| #408 | Command A+ medium | Cohere | 0.3 | 0.3 | $0.064 | 0/3 | 92.1s |
| #67 | MiMo-V2.6-Pro medium | Xiaomi | 0.8 | 0.9 | $0.586 | 2/3 | 92.2s |
| #302 | Step 5 Preview low | Stepfun | 0.8 | 0.6 | $4.110 | 2/3 | 95.0s |
| #418 | Command A+ low | Cohere | 0.3 | 0.3 | $0.073 | 0/3 | 95.8s |
| #380 | Granite 4.2 8B none | IBM Granite | 0.3 | 0.4 | $0.037 | 0/3 | 107.6s |
| #44 | Muse Spark Open xhigh | Meta | 0.8 | 0.9 | $2.081 | 2/3 | 112.5s |
| #36 | Qwen3.8 Max (0902) high | Qwen | 1.0 | 0.9 | $3.306 | 3/3 | 134.1s |