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。
| 排名 | 模型 | 公司 | 谜题求解 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #20 | Gemini 3.5 Flash none | 10.0 | 8.1 | 3/3 | 3.13s | |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 7.9 | 3/3 | 32.5s |
| #26 | Qwen3.6 Plus medium | Qwen | 10.0 | 7.9 | 3/3 | 6.34s |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 7.8 | 3/3 | 17.9s |
| #32 | Gemini 3.5 Flash minimal | 10.0 | 7.7 | 3/3 | 1.45s | |
| #34 | Qwen3.7 Max none | Qwen | 10.0 | 7.7 | 3/3 | 1.13s |
| #35 | Gemini 3 PRO Preview medium | 10.0 | 7.6 | 3/3 | 3.88s | |
| #37 | Gemma 4 26B A4B medium | 10.0 | 7.6 | 3/3 | 5.79s | |
| #50 | Gemini 3.1 Flash Lite Preview low | 10.0 | 7.4 | 3/3 | 1.69s | |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 7.4 | 3/3 | 5.31s |
| #58 | Gemini 3.1 Flash Lite Preview none | 10.0 | 7.2 | 3/3 | 900ms | |
| #61 | Gemini 3.1 Flash Lite low | 10.0 | 7.2 | 3/3 | 1.40s | |
| #63 | GPT-5.3 Chat none | OpenAI | 10.0 | 7.2 | 3/3 | 2.99s |
| #74 | Qwen3.6 Max Preview none | Qwen | 10.0 | 6.9 | 3/3 | 2.65s |
| #101 | Mimo V2 Omni none | Xiaomi | 10.0 | 6.0 | 3/3 | 1.16s |