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) |
|---|---|---|---|---|---|---|
| #145 | Laguna M.1 none | Poolside | 3.0 | 4.8 | 0/3 | 891ms |
| #147 | GPT-4o-mini none | OpenAI | 3.5 | 4.8 | 0/3 | 1.21s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 2.9 | 4.6 | 0/3 | 1.40s |
| #150 | Qwen3 Coder Next medium | Qwen | 3.0 | 4.6 | 0/3 | 1.25s |
| #151 | Trinity Large Preview none | Arcee AI | 3.6 | 4.6 | 0/3 | 1.97s |
| #153 | Qwen3.6 35B A3B none | Qwen | 3.2 | 4.6 | 0/3 | 1.07s |
| #154 | Qwen3.5-9B none | Qwen | 3.2 | 4.6 | 0/3 | 621ms |
| #155 | Mercury 2 none | Inception | 3.1 | 4.5 | 0/3 | 535ms |
| #156 | Hy3 preview none | Tencent | 3.1 | 4.4 | 0/3 | 4.56s |
| #157 | Grok 4.1 Fast none | X AI | 3.0 | 4.4 | 0/3 | 1.10s |
| #158 | GLM 4.7 Flash medium | Z.ai | 2.9 | 4.4 | 0/3 | 12.9s |
| #159 | Ling-2.6-1T none | Inclusionai | 3.1 | 4.3 | 0/3 | 5.36s |
| #160 | LFM2-24B-A2B none | Liquid | 3.8 | 4.2 | 0/3 | 1.78s |
| #161 | Qwen3.5-9B medium | Qwen | 3.0 | 4.2 | 0/3 | 32.3s |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.0 | 4.1 | 0/3 | 532ms |