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: 指标 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #273 | KAT-Coder-Pro V2.5 default | Kwaipilot | 0.8 | 0.6 | $0.742 | 2/3 | 3.03s |
| #274 | Apodex 1.1 Mini medium | Apodex | 0.8 | 0.6 | $0.000 | 2/3 | 15.2s |
| #341 | Mercury 2.5 Preview low | Inception | 0.8 | 0.5 | $0.015 | 2/3 | 710ms |
| #71 | Muse Spark 1.1 low | Meta | 0.8 | 0.9 | $0.885 | 2/3 | 6.60s |
| #143 | Space Bunny Alpha high | Stealth | 0.8 | 0.8 | $0.000 | 2/3 | 6.43s |
| #167 | Qwen3.8 27B medium | Qwen | 0.8 | 0.7 | ~$0.073 | 2/3 | 12.6s |
| #67 | MiMo-V2.6-Pro medium | Xiaomi | 0.8 | 0.9 | $0.586 | 2/3 | 92.2s |
| #101 | GPT-5.6 Terra medium | OpenAI | 0.8 | 0.8 | $0.483 | 2/3 | 3.78s |
| #61 | Muse Spark Open medium | Meta | 0.8 | 0.9 | $1.260 | 2/3 | 29.4s |
| #250 | Solar Pro 4 high | Upstage | 0.9 | 0.6 | $0.077 | 2/3 | 55.2s |
| #261 | GLM 5 Turbo medium | Z.ai | 0.9 | 0.6 | $0.323 | 2/3 | 5.23s |
| #112 | Qwen3.8 Flash Next low | Qwen | 0.9 | 0.8 | ~$0.045 | 2/3 | 1.72s |
| #24 | Claude Opus 5.5 low | Anthropic | 0.9 | 0.9 | $1.733 | 2/3 | 29.8s |
| #25 | Claude Opus 5.5 high | Anthropic | 0.9 | 0.9 | $2.133 | 2/3 | 30.8s |
| #39 | Muse Spark 1.3 high | Meta | 0.9 | 0.9 | $1.891 | 2/3 | 38.4s |