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) ↑.
451/451
Filter models
No models match the current search and filters.
| Rank | Model | Company | Puzzle Solving Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #74 | Claude Sonnet 5.5 high | Anthropic | 1.0 | 0.9 | $1.175 | 3/3 | 3.54s |
| #198 | GPT-5.6 Luna low | OpenAI | 0.8 | 0.7 | $0.049 | 2/3 | 3.59s |
| #7 | GPT-6 Astra high | OpenAI | 1.0 | 1.0 | $4.458 | 3/3 | 3.60s |
| #158 | DeepSeek V4 Pro 0423 none | DeepSeek | 1.0 | 0.7 | $0.083 | 3/3 | 3.61s |
| #178 | Claude Opus 5 none | Anthropic | 0.8 | 0.7 | $2.766 | 2/3 | 3.66s |
| #415 | Hunter Alpha default | OpenRouter | 0.6 | 0.3 | $0.000 | 1/3 | 3.71s |
| #103 | GPT-5.6 Terra medium | OpenAI | 0.8 | 0.8 | $0.483 | 2/3 | 3.78s |
| #134 | Muse Wonder high | Meta | 0.5 | 0.8 | $3.426 | 1/3 | 3.78s |
| #112 | GPT-5.4 Nano medium | OpenAI | 0.4 | 0.8 | $0.235 | 0/3 | 3.79s |
| #39 | Claude Haiku 5.5 xhigh | Anthropic | 0.8 | 0.9 | $0.140 | 2/3 | 3.80s |
| #301 | Trinity Large Thinking high | Arcee AI | 0.5 | 0.6 | $0.794 | 0/3 | 3.84s |
| #342 | MiMo-V2-Flash medium | Xiaomi | 0.8 | 0.5 | $0.043 | 2/3 | 3.87s |
| #117 | GLM 5.3 FlashX max | Z.ai | 0.8 | 0.8 | $0.623 | 2/3 | 3.88s |
| #359 | Gemini 3 PRO Preview medium | 1.0 | 0.5 | $0.385 | 3/3 | 3.88s | |
| #225 | Beam 1.0 501B A23B medium | Reflection | 1.0 | 0.7 | $0.499 | 3/3 | 3.91s |