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: Metric ↑.
| Rank | Model | Company | Puzzle Solving Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #94 | MiMo-V2-Flash none | Xiaomi | 3.6 | 4.5 | 0/3 | 1.38s |
| #81 | Elephant medium | Openrouter | 3.7 | 5.2 | 0/3 | 867ms |
| #89 | GPT-4o-mini none | OpenAI | 3.7 | 4.9 | 0/3 | 1.30s |
| #96 | GPT-5.4 Nano none | OpenAI | 3.7 | 4.5 | 0/3 | 1.29s |
| #80 | MiniMax M2.7 medium | Minimax | 3.8 | 5.3 | 0/3 | 25.6s |
| #63 | Qwen3.5-35B-A3B none | Qwen | 3.9 | 6.1 | 0/3 | 1.34s |
| #54 | Mercury 2 medium | Inception | 3.9 | 6.5 | 0/3 | 934ms |
| #38 | GPT-5.4 Nano medium | OpenAI | 4.0 | 7.6 | 0/3 | 3.65s |
| #74 | GLM 4.7 Flash none | Z.ai | 4.4 | 5.6 | 0/3 | 1.00s |
| #98 | LFM2-24B-A2B none | Liquid | 4.4 | 4.1 | 0/3 | 1.69s |
| #84 | gpt-oss-120b none | OpenAI | 4.5 | 5.2 | 0/3 | 6.86s |
| #34 | Kimi K2.6 medium | Moonshot AI | 5.0 | 7.7 | 0/3 | 25.6s |
| #61 | Seed-2.0-Lite none | Bytedance Seed | 5.2 | 6.2 | 1/3 | 2.46s |
| #71 | MiniMax M2.5 medium | Minimax | 5.3 | 5.7 | 1/3 | 11.5s |
| #82 | Grok 4.20 none | X AI | 5.3 | 5.2 | 1/3 | 487ms |