AI for Education Visual Maths — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 89.87 |
| 2 | GPT-5.4 (Medium) | 86.5 |
| 3 | Gemini 3 Pro | 80.59 |
| 4 | Gemini 3 Flash | 80.59 |
| 5 | Qwen 3.5 Plus | 80.17 |
| 6 | GPT-5.2 (Medium) | 78.48 |
| 7 | qwen3.5-flash | 76.79 |
| 8 | GPT-5.4 Mini (Medium) | 75.95 |
| 9 | Gemini 2.5 Pro | 73 |
| 10 | GPT-5 (Medium) | 71.73 |
| 11 | Claude Opus 4.7 | 71.31 |
| 12 | GPT-5 Mini (Medium) | 67.51 |
| 13 | O3 | 65.82 |
| 14 | Grok 4.20 (Reasoning) | 65.82 |
| 15 | Gemini 2.5 Flash | 63.29 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-maths · How the rankings work · Data refreshed daily, snapshot 2026-07-22.