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 ↑.
216/216
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） |
|---|---|---|---|---|---|---|---|
| #120 | Qwen3.5-Flash medium | Qwen | 8.2 | 6.2 | $0.139 | 2/3 | 27.6s |
| #125 | Qwen3.5-35B-A3B medium | Qwen | 8.2 | 6.2 | $0.837 | 2/3 | 33.1s |
| #27 | Muse Spark 1.1 low | Meta | 8.3 | 8.3 | $0.647 | 2/3 | 6.60s |
| #43 | GPT-5.6 Terra medium | OpenAI | 8.4 | 7.8 | $0.676 | 2/3 | 3.78s |
| #104 | Gemini 3.5 Flash-Lite medium | 8.4 | 6.5 | $0.369 | 2/3 | 1.70s | |
| #53 | GLM 5 Turbo medium | Z.ai | 8.7 | 7.6 | $0.323 | 2/3 | 5.23s |
| #16 | GPT-5.3-Codex medium | OpenAI | 9.0 | 8.9 | $0.920 | 2/3 | 5.05s |
| #39 | Seed-2.0-Lite medium | Bytedance Seed | 9.0 | 7.9 | $0.234 | 2/3 | 10.2s |
| #116 | Gemma 4 31B medium | 9.9 | 6.3 | $0.107 | 3/3 | 26.9s | |
| #1 | Gemini 3.6 Flash medium | 10.0 | 9.9 | $0.831 | 3/3 | 2.53s | |
| #2 | Gemini 3.6 Flash high | 10.0 | 9.7 | $1.785 | 3/3 | 3.04s | |
| #3 | Gemini 3 Flash Preview medium | 10.0 | 9.6 | $0.742 | 3/3 | 4.05s | |
| #4 | Gemini 3.5 Flash high | 10.0 | 9.5 | $1.976 | 3/3 | 3.23s | |
| #6 | Gemini 3.6 Flash low | 10.0 | 9.4 | $0.517 | 3/3 | 1.91s | |
| #8 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $1.234 | 3/3 | 4.10s |