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. Sort by: Tests Correct ↓.
| Rank | Model | Company | Puzzle Solving Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #91 | Mercury 2 none | Inception | 3.1 | 4.8 | 0/3 | 533ms |
| #92 | Qwen3 Coder Next medium | Qwen | 3.1 | 4.7 | 0/3 | 2.30s |
| #93 | GLM 4.7 Flash medium | Z.ai | 2.9 | 4.6 | 0/3 | 12.9s |
| #94 | MiMo-V2-Flash none | Xiaomi | 3.6 | 4.5 | 0/3 | 1.38s |
| #95 | Grok 4.1 Fast none | X AI | 3.2 | 4.5 | 0/3 | 1.28s |
| #96 | GPT-5.4 Nano none | OpenAI | 3.7 | 4.5 | 0/3 | 1.29s |
| #97 | Qwen3.5-9B medium | Qwen | 3.1 | 4.4 | 0/3 | 33.4s |
| #98 | LFM2-24B-A2B none | Liquid | 4.4 | 4.1 | 0/3 | 1.69s |