AI for Education Visual Maths - Number and Operations — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 83.78 |
| 2 | GPT-5.4 Mini (Medium) | 72.97 |
| 3 | Qwen 3.5 Plus | 72.97 |
| 4 | Gemini 3 Pro | 70.27 |
| 5 | GPT-5.4 (Medium) | 70.27 |
| 6 | GPT-5.2 (Medium) | 67.57 |
| 7 | qwen3.5-flash | 67.57 |
| 8 | Claude Sonnet 4.6 | 64.86 |
| 9 | Claude Opus 4.7 | 64.86 |
| 10 | Gemini 3 Flash | 64.86 |
| 11 | GPT-5 (Medium) | 64.86 |
| 12 | Grok 4.20 (Reasoning) | 62.16 |
| 13 | Gemini 2.5 Pro | 59.46 |
| 14 | GLM-4.6V | 59.46 |
| 15 | O3 | 56.76 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-maths-number-and-operations · How the rankings work · Data refreshed daily, snapshot 2026-07-22.