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) |
|---|---|---|---|---|---|---|
| #2 | Gemini 3.1 Pro Preview medium | 10.0 | 9.6 | 3/3 | 7.15s | |
| #84 | gpt-oss-120b none | OpenAI | 4.5 | 5.2 | 0/3 | 6.86s |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 10.0 | 8.5 | 3/3 | 6.11s |
| #20 | Qwen3.6 Plus medium | Qwen | 10.0 | 8.1 | 3/3 | 6.11s |
| #5 | Gemini 3 Flash Preview low | 10.0 | 8.8 | 3/3 | 6.11s | |
| #59 | Qwen3.5-Flash none | Qwen | 3.3 | 6.2 | 0/3 | 5.90s |
| #40 | GPT-5.2 medium | OpenAI | 7.7 | 7.5 | 2/3 | 5.47s |
| #18 | GLM 5 Turbo medium | Z.ai | 7.3 | 8.1 | 1/3 | 5.44s |
| #50 | Hunter Alpha medium | OpenRouter | 6.1 | 6.7 | 1/3 | 5.36s |
| #7 | GPT-5.3-Codex medium | OpenAI | 9.0 | 8.6 | 2/3 | 5.12s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 7.2 | 6.4 | 1/3 | 5.01s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 8.0 | 3/3 | 4.80s |
| #76 | Kimi K2.5 none | Moonshot AI | 3.1 | 5.5 | 0/3 | 4.73s |
| #23 | MiMo-V2-Pro medium | Xiaomi | 7.0 | 8.1 | 1/3 | 4.71s |
| #37 | Claude Opus 4.6 medium | Anthropic | 7.7 | 7.6 | 2/3 | 4.60s |