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） |
|---|---|---|---|---|---|---|---|
| #209 | Ember-1 max | Fireworks | 0.8 | 0.7 | $3.264 | 2/3 | 6.57s |
| #211 | GPT-5.6 Sol none | OpenAI | 0.8 | 0.7 | $0.795 | 2/3 | 1.49s |
| #212 | Apodex 1.1 Mini high | Apodex | 0.8 | 0.7 | $0.000 | 2/3 | 13.5s |
| #213 | GLM 5.3 Flash low | Z.ai | 0.8 | 0.7 | $0.038 | 2/3 | 2.67s |
| #214 | GPT-5.5 none | OpenAI | 0.8 | 0.7 | $1.212 | 2/3 | 1.29s |
| #215 | GLM 5.2 none | Z.ai | 0.8 | 0.7 | $0.250 | 2/3 | 3.31s |
| #222 | Claude Sonnet 5.5 medium | Anthropic | 0.8 | 0.7 | $1.100 | 2/3 | 2.43s |
| #223 | Qwen3.6 35B A3B medium | Qwen | 0.8 | 0.7 | $0.834 | 2/3 | 5.95s |
| #225 | Mercury 2.5 high | Inception | 0.9 | 0.6 | $0.044 | 2/3 | 1.39s |
| #228 | GLM 5.1 none | Z.ai | 0.8 | 0.6 | $0.451 | 2/3 | 1.45s |
| #229 | KAT-Coder-Pro V2.5 high | Kwaipilot | 0.8 | 0.6 | $0.506 | 2/3 | 3.38s |
| #233 | Gemini 3 Flash Preview none | 0.8 | 0.6 | $0.155 | 2/3 | 1.05s | |
| #234 | Beam 1.0 501B A23B max | Reflection | 0.8 | 0.6 | $0.799 | 2/3 | 3.94s |
| #235 | Solar Pro 4 medium | Upstage | 0.9 | 0.6 | $0.098 | 2/3 | 45.8s |
| #245 | Qwen3.5-35B-A3B medium | Qwen | 0.8 | 0.6 | $0.716 | 2/3 | 33.1s |