Puzzle Solving Ranking
See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Score ↓.
442/442
Filter models
No models match the current search and filters.
| Rank | Model | Company | Puzzle Solving Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #1 | Gemini 3.6 Flash high | 1.0 | 1.0 | $0.900 | 3/3 | 3.36s | |
| #2 | Gemini 3.8 Flash high | 1.0 | 1.0 | $1.927 | 3/3 | 3.44s | |
| #3 | GPT-6 Sol high | OpenAI | 1.0 | 1.0 | $0.921 | 3/3 | 16.9s |
| #4 | GPT-6.1 Sol max | OpenAI | 1.0 | 1.0 | $1.006 | 3/3 | 7.67s |
| #5 | GPT-6 Astra max | OpenAI | 1.0 | 1.0 | $5.044 | 3/3 | 7.32s |
| #6 | GPT-6.1 Sol xhigh | OpenAI | 1.0 | 1.0 | $1.377 | 3/3 | 4.87s |
| #7 | GPT-6 Astra high | OpenAI | 1.0 | 1.0 | $4.458 | 3/3 | 3.60s |
| #8 | GPT-6 Astra xhigh | OpenAI | 1.0 | 1.0 | $6.213 | 3/3 | 4.48s |
| #9 | Gemini 3.7 Flash high | 1.0 | 1.0 | $0.528 | 3/3 | 2.76s | |
| #10 | Gemini 3.6 Flash medium | 1.0 | 1.0 | $0.577 | 3/3 | 3.43s | |
| #440 | Tev1 4B Experimental default | Togethercomputer | 0.2 | 1.0 | $0.002 | 0/1 | 432ms |
| #11 | GPT-6.1 Sol medium | OpenAI | 1.0 | 1.0 | $0.530 | 3/3 | 2.99s |
| #12 | GPT-6.1 Sol high | OpenAI | 1.0 | 1.0 | $0.755 | 3/3 | 3.99s |
| #13 | GPT-5.6 Sol low | OpenAI | 0.8 | 1.0 | $1.244 | 2/3 | 3.44s |
| #14 | GPT-6 Astra low | OpenAI | 1.0 | 1.0 | $2.160 | 3/3 | 2.44s |