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） |
|---|---|---|---|---|---|---|---|
| #120 | Qwen3.8 2.4T A95B high | Qwen | 1.0 | 0.8 | $2.949 | 3/3 | 65.5s |
| #160 | Grok 4.7 medium | X AI | 1.0 | 0.7 | $2.938 | 3/3 | 18.5s |
| #28 | Claude Opus 5 medium | Anthropic | 1.0 | 0.9 | $2.870 | 3/3 | 4.27s |
| #175 | Claude Opus 5 none | Anthropic | 0.8 | 0.7 | $2.766 | 2/3 | 3.66s |
| #92 | Gemini 3.5 Flash high | 1.0 | 0.8 | $2.737 | 3/3 | 3.23s | |
| #21 | GPT-6 Astra medium | OpenAI | 1.0 | 0.9 | $2.707 | 3/3 | 2.54s |
| #99 | Grok 4.5 high | X AI | 1.0 | 0.8 | $2.687 | 3/3 | 7.88s |
| #40 | Muse Wonder low | Meta | 0.6 | 0.9 | $2.637 | 1/3 | 5.08s |
| #76 | Grok 4.6 high | X AI | 1.0 | 0.9 | $2.629 | 3/3 | 15.6s |
| #87 | Muse Spark 1.1 high | Meta | 0.8 | 0.8 | $2.570 | 2/3 | 70.0s |
| #191 | Ember-1 high | Fireworks | 1.0 | 0.7 | $2.405 | 3/3 | 4.84s |
| #50 | Claude Opus 5 low | Anthropic | 1.0 | 0.9 | $2.350 | 3/3 | 4.23s |
| #195 | Claude Opus 4.8 none | Anthropic | 0.8 | 0.7 | $2.334 | 2/3 | 2.74s |
| #383 | Gemini 3.1 Flash Lite Preview high | 0.8 | 0.4 | $2.310 | 2/3 | 46.7s | |
| #127 | Grok 4.6 medium | X AI | 0.9 | 0.8 | $2.270 | 2/3 | 16.3s |