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） |
|---|---|---|---|---|---|---|---|
| #133 | Muse Glimmer 30B high | Meta | 0.6 | 0.8 | $0.506 | 1/3 | 64.8s |
| #392 | Hunter Alpha medium | OpenRouter | 0.6 | 0.4 | $0.000 | 1/3 | 5.35s |
| #311 | Gemma 4 26B A4B none | 0.6 | 0.5 | $0.031 | 1/3 | 744ms | |
| #282 | Gemini 3.1 Flash Lite none | 0.6 | 0.6 | $0.069 | 1/3 | 720ms | |
| #256 | Trinity Large Thinking low | Arcee AI | 0.6 | 0.6 | $0.918 | 1/3 | 3.28s |
| #287 | Qwen3.8 Flash Next none | Qwen | 0.6 | 0.6 | ~$0.011 | 1/3 | 1.30s |
| #413 | Grok Build 0.1 none | X AI | 0.6 | 0.3 | $0.547 | 1/3 | 9.55s |
| #198 | Inkling low | Thinkingmachines | 0.6 | 0.7 | $0.293 | 1/3 | 2.97s |
| #357 | GLM 4.7 Flash none | Z.ai | 0.6 | 0.5 | $0.027 | 1/3 | 1.20s |
| #62 | DeepSeek V4.1 Flash high | DeepSeek | 0.6 | 0.9 | $0.617 | 1/3 | 14.3s |
| #221 | KAT-Coder-Pro V2.5 low | Kwaipilot | 0.6 | 0.7 | $0.568 | 1/3 | 3.11s |
| #332 | Mimo V2 PRO medium | Xiaomi | 0.6 | 0.5 | $0.333 | 1/3 | 5.08s |
| #298 | Gemma 4 31B none | 0.6 | 0.6 | $0.031 | 1/3 | 4.23s | |
| #165 | Qwen3.5-27B none | Qwen | 0.7 | 0.7 | $0.116 | 1/3 | 1.38s |
| #241 | MiMo-V2.5-Pro medium | Xiaomi | 0.7 | 0.6 | $0.332 | 1/3 | 5.31s |