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: 总成本 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #68 | Seed 2.1 Turbo medium | Bytedance Seed | 1.0 | 0.9 | $2.042 | 3/3 | 21.0s |
| #366 | Gemini 3.1 Flash Lite high | 0.6 | 0.5 | $2.044 | 1/3 | 50.8s | |
| #44 | Muse Spark Open xhigh | Meta | 0.8 | 0.9 | $2.081 | 2/3 | 112.5s |
| #236 | Claude Sonnet 4.6 medium | Anthropic | 1.0 | 0.6 | $2.126 | 3/3 | 5.31s |
| #25 | Claude Opus 5.5 high | Anthropic | 0.9 | 0.9 | $2.133 | 2/3 | 30.8s |
| #14 | GPT-6 Astra low | OpenAI | 1.0 | 1.0 | $2.160 | 3/3 | 2.44s |
| #60 | GPT-5.4 medium | OpenAI | 0.8 | 0.9 | $2.213 | 2/3 | 9.14s |
| #127 | Grok 4.6 medium | X AI | 0.9 | 0.8 | $2.270 | 2/3 | 16.3s |
| #383 | Gemini 3.1 Flash Lite Preview high | 0.8 | 0.4 | $2.310 | 2/3 | 46.7s | |
| #195 | Claude Opus 4.8 none | Anthropic | 0.8 | 0.7 | $2.334 | 2/3 | 2.74s |
| #50 | Claude Opus 5 low | Anthropic | 1.0 | 0.9 | $2.350 | 3/3 | 4.23s |
| #191 | Ember-1 high | Fireworks | 1.0 | 0.7 | $2.405 | 3/3 | 4.84s |
| #87 | Muse Spark 1.1 high | Meta | 0.8 | 0.8 | $2.570 | 2/3 | 70.0s |
| #76 | Grok 4.6 high | X AI | 1.0 | 0.9 | $2.629 | 3/3 | 15.6s |
| #40 | Muse Wonder low | Meta | 0.6 | 0.9 | $2.637 | 1/3 | 5.08s |