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） |
|---|---|---|---|---|---|---|---|
| #437 | Solar Decide Flash default | Upstage | 1.0 | 0.2 | $0.003 | 0/1 | 1.66s |
| #438 | Microsoft-Decision-1 default | Microsoft | 0.2 | 0.1 | $0.002 | 0/1 | 669ms |
| #439 | Solar Decide default | Upstage | 1.0 | 0.1 | $0.009 | 0/1 | 3.47s |
| #440 | Tev1 4B Experimental default | Togethercomputer | 0.2 | 1.0 | $0.002 | 0/1 | 432ms |
| #441 | Nimble v3 9B default | Bespoke Labs | 0.2 | 0.8 | ~$0.001 | 0/1 | 79ms |
| #442 | Claude Opus 5.5 none | Anthropic | 0.0 | 0.2 | $0.015 | 0/0 | 0ms |
| #40 | Muse Wonder low | Meta | 0.6 | 0.9 | $2.637 | 1/3 | 5.08s |
| #43 | Muse Wonder minimal | Meta | 0.5 | 0.9 | $1.639 | 1/3 | 1.36s |
| #62 | DeepSeek V4.1 Flash high | DeepSeek | 0.6 | 0.9 | $0.617 | 1/3 | 14.3s |
| #70 | DeepSeek V4.1 Flash max | DeepSeek | 0.6 | 0.9 | $1.204 | 1/3 | 30.8s |
| #83 | GPT-5 Mini medium | OpenAI | 0.6 | 0.8 | $0.315 | 1/3 | 15.2s |
| #86 | Inkling high | Thinkingmachines | 0.7 | 0.8 | $1.238 | 1/3 | 10.7s |
| #89 | GLM 5.2 high | Z.ai | 0.6 | 0.8 | $4.632 | 1/3 | 33.7s |
| #91 | Claude Haiku 5.5 high | Anthropic | 0.6 | 0.8 | $0.088 | 1/3 | 3.28s |
| #104 | DeepSeek V4 Pro 0423 high | DeepSeek | 0.7 | 0.8 | $0.149 | 1/3 | 56.8s |