AI for Education Visual Maths - Measurement — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 97.3 |
| 2 | qwen3.5-flash | 97.3 |
| 3 | GPT-5.4 (Medium) | 97.3 |
| 4 | GPT-5.4 Mini (Medium) | 94.59 |
| 5 | GPT-5.2 (Medium) | 94.59 |
| 6 | GPT-5 (Medium) | 94.59 |
| 7 | Gemini 2.5 Pro | 91.89 |
| 8 | Claude Opus 4.7 | 91.89 |
| 9 | GPT-5 Mini (Medium) | 91.89 |
| 10 | Qwen 3.5 Plus | 91.89 |
| 11 | O3 | 89.19 |
| 12 | Gemini 3 Pro | 89.19 |
| 13 | O4 Mini | 89.19 |
| 14 | Grok 4 | 86.49 |
| 15 | Gemini 3 Flash | 86.49 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-maths-measurement · How the rankings work · Data refreshed daily, snapshot 2026-07-22.