AI BENCHY Category
Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear.
| Rank | Model | Company | Puzzle Solving Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #77 | Claude Sonnet 4.6 none | Anthropic | 7.7 | 6.8 | 2/3 | 2.53s |
| #78 | Qwen3.6 27B medium | Qwen | 7.7 | 6.8 | 2/3 | 61.1s |
| #82 | Hy3 preview high | Tencent | 7.7 | 6.6 | 2/3 | 27.9s |
| #88 | Qwen3.7 Plus none | Qwen | 7.7 | 6.4 | 2/3 | 1.71s |
| #91 | GPT-5.5 none | OpenAI | 7.7 | 6.4 | 2/3 | 1.29s |
| #95 | Qwen3.5 Plus 2026-02-15 none | Qwen | 7.7 | 6.3 | 2/3 | 2.71s |
| #96 | Ring-2.6-1T none | Inclusionai | 7.7 | 6.2 | 2/3 | 31.5s |
| #97 | Gemini 2.5 Flash none | 7.7 | 6.2 | 2/3 | 604ms | |
| #98 | GLM 5 none | Z.ai | 7.7 | 6.1 | 2/3 | 1.91s |
| #106 | Grok 4.20 Beta none | X AI | 7.7 | 5.8 | 2/3 | 586ms |
| #112 | GLM 5.1 none | Z.ai | 7.7 | 5.7 | 2/3 | 1.45s |
| #44 | Gemini 3.1 Flash Lite medium | 7.6 | 7.5 | 2/3 | 1.95s | |
| #113 | DeepSeek V4 Pro none | DeepSeek | 7.6 | 5.7 | 2/3 | 16.0s |
| #133 | DeepSeek V3.2 none | DeepSeek | 7.6 | 5.2 | 2/3 | 6.91s |
| #42 | GPT-5.2 medium | OpenAI | 7.5 | 7.5 | 2/3 | 5.80s |