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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #108 | Laguna XS 2.1 medium | Poolside | 5.3 | 6.5 | $0.068 | 1/3 | 3.43s |
| #109 | Qwen3.5-27B none | Qwen | 6.7 | 6.5 | $0.090 | 1/3 | 1.38s |
| #114 | Ring-2.6-1T medium | Inclusionai | 5.9 | 6.3 | $0.103 | 1/3 | 20.7s |
| #115 | Mimo V2 PRO medium | Xiaomi | 6.4 | 6.3 | $0.333 | 1/3 | 5.08s |
| #118 | Claude Sonnet 5 none | Anthropic | 6.0 | 6.3 | $0.548 | 1/3 | 3.22s |
| #121 | Gemma 4 31B none | 6.5 | 6.2 | $0.021 | 1/3 | 4.23s | |
| #122 | Seed-2.0-Lite none | Bytedance Seed | 5.3 | 6.2 | $0.066 | 1/3 | 2.78s |
| #126 | Gemini 3.1 Flash Lite minimal | 6.0 | 6.1 | $0.047 | 1/3 | 2.15s | |
| #127 | gpt-oss-120b medium | OpenAI | 5.3 | 6.1 | $0.019 | 1/3 | 21.7s |
| #128 | Gemini 3.1 Flash Lite none | 6.3 | 6.1 | $0.046 | 1/3 | 720ms | |
| #129 | Inkling low | Thinkingmachines | 6.4 | 6.1 | $0.187 | 1/3 | 2.97s |
| #132 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.7 | 6.1 | $0.122 | 1/3 | 1.97s |
| #134 | GPT-5 Nano medium | OpenAI | 5.3 | 6.1 | $0.114 | 1/3 | 20.6s |
| #135 | Nemotron 3 Ultra none | NVIDIA | 5.9 | 6.1 | $0.095 | 1/3 | 1.06s |
| #136 | Step 3.5 Flash medium | Stepfun | 5.3 | 6.0 | $0.108 | 1/3 | 7.22s |