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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #95 | GPT-6 Luna medium | OpenAI | 0.8 | 0.8 | $0.047 | 2/3 | 9.78s |
| #121 | Gemini 3.5 Flash medium | 0.8 | 0.8 | $1.316 | 2/3 | 2.38s | |
| #124 | Muse Wonder max | Meta | 0.8 | 0.8 | $4.766 | 2/3 | 8.97s |
| #131 | Qwen3.7 Plus none | Qwen | 0.8 | 0.8 | $0.178 | 2/3 | 1.71s |
| #144 | GPT-6 Luna low | OpenAI | 0.8 | 0.8 | $0.033 | 2/3 | 27.5s |
| #145 | Qwen3.8 27B low | Qwen | 0.8 | 0.8 | ~$0.089 | 2/3 | 4.91s |
| #164 | Gemini 2.5 Flash medium | 0.8 | 0.7 | $0.680 | 2/3 | 3.18s | |
| #177 | Qwen3.6 27B medium | Qwen | 0.8 | 0.7 | $1.021 | 2/3 | 61.1s |
| #178 | Claude Opus 5 none | Anthropic | 0.8 | 0.7 | $2.766 | 2/3 | 3.66s |
| #179 | Qwen3.8 Flash Next xhigh | Qwen | 0.8 | 0.7 | ~$0.195 | 2/3 | 19.5s |
| #181 | Minimax M3.1 Flash low | Minimax | 0.8 | 0.7 | $0.000 | 2/3 | 2.12s |
| #184 | GPT-5.2 Chat default | OpenAI | 0.8 | 0.7 | $0.594 | 2/3 | 4.10s |
| #186 | Gemini 3.1 Flash Lite Preview medium | 0.8 | 0.7 | $0.158 | 2/3 | 5.30s | |
| #193 | Muse Glimmer 30B low | Meta | 0.8 | 0.7 | $0.219 | 2/3 | 5.06s |
| #194 | Minimax M3.1 Flash max | Minimax | 0.8 | 0.7 | $0.000 | 2/3 | 3.34s |