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: 总成本 ↓.
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） |
|---|---|---|---|---|---|---|---|
| #34 | Claude Sonnet 5.5 max | Anthropic | 1.0 | 0.9 | $8.557 | 3/3 | 6.17s |
| #8 | GPT-6 Astra xhigh | OpenAI | 1.0 | 1.0 | $6.213 | 3/3 | 4.48s |
| #391 | Grok 4.20 Multi Agent Beta medium | X AI | 0.7 | 0.4 | $5.599 | 1/3 | 5.19s |
| #57 | Claude Fable 5 medium | Anthropic | 0.8 | 0.9 | $5.089 | 2/3 | 5.18s |
| #5 | GPT-6 Astra max | OpenAI | 1.0 | 1.0 | $5.044 | 3/3 | 7.32s |
| #33 | GPT-5.5 medium | OpenAI | 1.0 | 0.9 | $4.809 | 3/3 | 6.76s |
| #122 | Muse Wonder max | Meta | 0.8 | 0.8 | $4.766 | 2/3 | 8.97s |
| #89 | GLM 5.2 high | Z.ai | 0.6 | 0.8 | $4.632 | 1/3 | 33.7s |
| #27 | Claude Opus 5 high | Anthropic | 1.0 | 0.9 | $4.524 | 3/3 | 4.66s |
| #185 | Step 5 Preview high | Stepfun | 0.6 | 0.7 | $4.513 | 1/3 | 143.2s |
| #7 | GPT-6 Astra high | OpenAI | 1.0 | 1.0 | $4.458 | 3/3 | 3.60s |
| #271 | Step 5 Preview medium | Stepfun | 0.8 | 0.6 | $4.136 | 2/3 | 59.9s |
| #302 | Step 5 Preview low | Stepfun | 0.8 | 0.6 | $4.110 | 2/3 | 95.0s |
| #82 | Qwen3.8 2.4T A95B low | Qwen | 1.0 | 0.8 | $4.016 | 3/3 | 43.4s |
| #139 | Muse Wonder xhigh | Meta | 0.5 | 0.8 | $4.012 | 1/3 | 3.53s |