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: Response Time (avg) ↑.
| Rank | Model | Company | Puzzle Solving Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #98 | GLM 5 none | Z.ai | 7.7 | 6.1 | 2/3 | 1.91s |
| #107 | Laguna Xs.2 medium | Poolside | 5.3 | 5.8 | 1/3 | 1.93s |
| #44 | Gemini 3.1 Flash Lite medium | 7.6 | 7.5 | 2/3 | 1.95s | |
| #151 | Trinity Large Preview none | Arcee AI | 3.6 | 4.6 | 0/3 | 1.97s |
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 6.7 | 5.7 | 1/3 | 1.97s |
| #143 | MiMo-V2.5 none | Xiaomi | 5.4 | 4.9 | 1/3 | 2.13s |
| #87 | Gemini 3.1 Flash Lite minimal | 6.0 | 6.4 | 1/3 | 2.15s | |
| #132 | Mistral Small 4 medium | Mistral | 3.4 | 5.3 | 0/3 | 2.17s |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 3/3 | 2.35s | |
| #141 | Nemotron 3 Super none | NVIDIA | 5.5 | 4.9 | 1/3 | 2.36s |
| #80 | Mimo V2 Omni medium | Xiaomi | 5.9 | 6.7 | 1/3 | 2.38s |
| #7 | Gemini 3.5 Flash medium | 7.7 | 9.0 | 2/3 | 2.38s | |
| #109 | GLM 5V Turbo none | Z.ai | 5.3 | 5.8 | 1/3 | 2.40s |
| #11 | Claude Opus 4.7 medium | Anthropic | 10.0 | 8.7 | 3/3 | 2.43s |
| #8 | Claude Opus 4.7 none | Anthropic | 10.0 | 8.9 | 3/3 | 2.46s |