AI BENCHY 分类
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 ↑.
| 排名 | 模型 | 公司 | 谜题求解 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #103 | DeepSeek V4 Pro high | DeepSeek | 5.9 | 6.0 | 1/3 | 34.8s |
| #104 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 5.9 | 6.0 | 1/3 | 1.06s |
| #107 | Laguna Xs.2 medium | Poolside | 5.3 | 5.8 | 1/3 | 1.93s |
| #109 | GLM 5V Turbo none | Z.ai | 5.3 | 5.8 | 1/3 | 2.40s |
| #110 | Seed-2.0-Lite none | Bytedance Seed | 5.3 | 5.8 | 1/3 | 2.78s |
| #111 | Owl Alpha medium | Openrouter | 5.3 | 5.7 | 1/3 | 3.40s |
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.7 | 5.7 | 1/3 | 1.97s |
| #115 | Qwen3.5-27B none | Qwen | 6.7 | 5.7 | 1/3 | 1.38s |
| #116 | Hunter Alpha none | OpenRouter | 5.8 | 5.7 | 1/3 | 3.71s |
| #118 | Qwen3.6 27B none | Qwen | 5.3 | 5.6 | 1/3 | 5.15s |
| #120 | Mimo V2 PRO none | Xiaomi | 6.0 | 5.6 | 1/3 | 1.61s |
| #121 | Owl Alpha none | Openrouter | 5.4 | 5.5 | 1/3 | 4.18s |
| #122 | GLM 4.7 Flash none | Z.ai | 6.4 | 5.5 | 1/3 | 1.20s |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 6.7 | 5.5 | 1/3 | 1.30s |
| #125 | GPT-5.4 none | OpenAI | 5.6 | 5.5 | 1/3 | 1.44s |