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） ↓.
451/451
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） |
|---|---|---|---|---|---|---|---|
| #229 | Qwen3.6 35B A3B medium | Qwen | 0.8 | 0.7 | $0.834 | 2/3 | 5.95s |
| #47 | Qwen3.8 Max (0902) medium | Qwen | 1.0 | 0.9 | $1.096 | 3/3 | 5.89s |
| #66 | GPT-5.2 medium | OpenAI | 0.7 | 0.9 | $1.558 | 2/3 | 5.80s |
| #160 | Gemma 4 26B A4B medium | 1.0 | 0.7 | $0.101 | 3/3 | 5.79s | |
| #192 | Gemini 3 Flash Preview low | 1.0 | 0.7 | $0.254 | 3/3 | 5.77s | |
| #126 | DeepSeek V4.1 Flash 1017 high | DeepSeek | 0.5 | 0.8 | $0.589 | 1/3 | 5.70s |
| #162 | Claude Fable 5.1 medium | Anthropic | 0.8 | 0.7 | $3.197 | 2/3 | 5.70s |
| #53 | GLM 5.3 Flash max | Z.ai | 0.9 | 0.9 | $0.089 | 2/3 | 5.61s |
| #91 | GPT-5.6 Terra high | OpenAI | 0.8 | 0.8 | $0.698 | 2/3 | 5.45s |
| #267 | Space Bunny Alpha xhigh | Stealth | 0.8 | 0.6 | $0.000 | 2/3 | 5.45s |
| #360 | Ling 2.6 1t default | Inclusionai | 0.3 | 0.5 | $0.016 | 0/3 | 5.36s |
| #401 | Hunter Alpha medium | OpenRouter | 0.6 | 0.4 | $0.000 | 1/3 | 5.35s |
| #248 | MiMo-V2.5-Pro medium | Xiaomi | 0.7 | 0.6 | $0.332 | 1/3 | 5.31s |
| #242 | Claude Sonnet 4.6 medium | Anthropic | 1.0 | 0.6 | $2.126 | 3/3 | 5.31s |
| #186 | Gemini 3.1 Flash Lite Preview medium | 0.8 | 0.7 | $0.158 | 2/3 | 5.30s |