AI for Education Visual Maths - Geometry — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 88.46 |
| 2 | GPT-5.4 (Medium) | 86.92 |
| 3 | Gemini 3 Flash | 82.31 |
| 4 | Gemini 3 Pro | 80.77 |
| 5 | Qwen 3.5 Plus | 77.69 |
| 6 | GPT-5.2 (Medium) | 76.92 |
| 7 | qwen3.5-flash | 73.08 |
| 8 | GPT-5.4 Mini (Medium) | 69.23 |
| 9 | Gemini 2.5 Pro | 68.46 |
| 10 | Claude Opus 4.7 | 66.15 |
| 11 | GPT-5 (Medium) | 63.85 |
| 12 | Grok 4.20 (Reasoning) | 62.31 |
| 13 | GPT-5 Mini (Medium) | 61.54 |
| 14 | Gemini 2.5 Flash | 60 |
| 15 | O3 | 58.46 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-maths-geometry · How the rankings work · Data refreshed daily, snapshot 2026-07-22.