AI for Education Visual Maths: leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 76 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 91.14 |
| 2 | GPT-5.5 | 89.87 |
| 3 | Gemini 3.7 Flash | 89.45 |
| 4 | Claude Fable 5 | 86.92 |
| 5 | GPT-5.4 (Medium) | 86.5 |
| 6 | Gemini 3.1 Pro (Preview) | 82.7 |
| 7 | Qwen 3.6 Plus | 80.59 |
| 8 | Gemini 3 Flash | 80.59 |
| 9 | Gemini 3 Pro | 80.59 |
| 10 | Claude Opus 5 | 80.59 |
| 11 | Qwen 3.5 Plus | 80.17 |
| 12 | GPT-5.2 (Medium) | 78.48 |
| 13 | Gemini 3.6 Flash | 78.48 |
| 14 | Grok 4.5 | 77.64 |
| 15 | Qwen 3.5 Flash | 76.79 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-maths · How It Works · Data refreshed daily, snapshot 2026-09-05.