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: 测试正确 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #14 | GPT-6 Astra low | OpenAI | 1.0 | 1.0 | $2.160 | 3/3 | 2.44s |
| #15 | Gemini 3 Flash Preview medium | 1.0 | 1.0 | $0.876 | 3/3 | 4.05s | |
| #16 | GPT-6.1 Sol low | OpenAI | 1.0 | 1.0 | $0.460 | 3/3 | 2.19s |
| #17 | Gemini 4 Argon high | 1.0 | 1.0 | $1.802 | 3/3 | 4.46s | |
| #18 | Gemini 3.7 Flash medium | 1.0 | 1.0 | $0.278 | 3/3 | 2.33s | |
| #19 | GPT-6 Sol medium | OpenAI | 1.0 | 0.9 | $0.703 | 3/3 | 2.79s |
| #21 | GPT-6 Astra medium | OpenAI | 1.0 | 0.9 | $2.707 | 3/3 | 2.54s |
| #22 | GPT-5.6 Sol high | OpenAI | 1.0 | 0.9 | $1.595 | 3/3 | 4.10s |
| #23 | GPT-5.5 low | OpenAI | 1.0 | 0.9 | $1.822 | 3/3 | 4.74s |
| #26 | Gemini 3.7 Flash low | 1.0 | 0.9 | $0.183 | 3/3 | 1.92s | |
| #27 | Claude Opus 5 high | Anthropic | 1.0 | 0.9 | $4.524 | 3/3 | 4.66s |
| #28 | Claude Opus 5 medium | Anthropic | 1.0 | 0.9 | $2.870 | 3/3 | 4.27s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 1.0 | 0.9 | $1.645 | 3/3 | 23.5s |
| #31 | Claude Opus 5.5 medium | Anthropic | 1.0 | 0.9 | $1.804 | 3/3 | 30.1s |
| #33 | GPT-5.5 medium | OpenAI | 1.0 | 0.9 | $4.809 | 3/3 | 6.76s |