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） |
|---|---|---|---|---|---|---|---|
| #163 | Qwen3.6 Plus medium | Qwen | 1.0 | 0.7 | $0.554 | 3/3 | 6.34s |
| #200 | GPT-6 Sol none | OpenAI | 0.8 | 0.7 | $0.551 | 2/3 | 1.40s |
| #413 | Grok Build 0.1 none | X AI | 0.6 | 0.3 | $0.547 | 1/3 | 9.55s |
| #210 | GPT 5.3 Chat default | OpenAI | 1.0 | 0.7 | $0.533 | 3/3 | 2.99s |
| #11 | GPT-6.1 Sol medium | OpenAI | 1.0 | 1.0 | $0.530 | 3/3 | 2.99s |
| #9 | Gemini 3.7 Flash high | 1.0 | 1.0 | $0.528 | 3/3 | 2.76s | |
| #156 | Inkling medium | Thinkingmachines | 1.0 | 0.7 | $0.527 | 3/3 | 5.18s |
| #80 | Claude Haiku 5.5 max | Anthropic | 1.0 | 0.8 | $0.509 | 3/3 | 16.5s |
| #240 | Gemini 3.5 Flash minimal | 1.0 | 0.6 | $0.508 | 3/3 | 1.45s | |
| #229 | KAT-Coder-Pro V2.5 high | Kwaipilot | 0.8 | 0.6 | $0.506 | 2/3 | 3.38s |
| #133 | Muse Glimmer 30B high | Meta | 0.6 | 0.8 | $0.506 | 1/3 | 64.8s |
| #314 | Claude Opus 4.7 none | Anthropic | 1.0 | 0.5 | $0.505 | 3/3 | 2.46s |
| #220 | Beam 1.0 501B A23B medium | Reflection | 1.0 | 0.7 | $0.499 | 3/3 | 3.91s |
| #125 | GLM 5.3 high | Z.ai | 0.8 | 0.8 | $0.495 | 2/3 | 4.74s |
| #107 | DeepSeek V4.1 Flash low | DeepSeek | 0.8 | 0.8 | $0.494 | 2/3 | 9.39s |