AI for Education Visual Reasoning - match (figure): leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.7 Flash | 87.4 |
| 2 | Gemini 3.5 Flash | 85.2 |
| 3 | Gemini 3.6 Flash | 84.7 |
| 4 | Gemini 3.1 Pro (Preview) | 82 |
| 5 | GPT-5.6 Sol | 77 |
| 6 | Gemini 3 Flash | 76 |
| 7 | GPT-5.5 | 74.3 |
| 8 | Gemini 3 Pro | 73.8 |
| 9 | Qwen 3.5 397B A17B | 69.9 |
| 10 | GPT-5.4 (Medium) | 69.4 |
| 11 | Qwen 3.6 Plus | 67.8 |
| 12 | Qwen 3.5 Plus | 67.2 |
| 13 | Kimi K3 | 63.9 |
| 14 | Kimi K2.5 | 63.4 |
| 15 | Gemini 2.5 Pro | 60.7 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-reasoning-match-figure · How It Works · Data refreshed daily, snapshot 2026-09-05.