AI for Education Visual Reasoning - match (process) — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 64 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 88.9 |
| 2 | Gemini 3 Flash | 77.8 |
| 3 | GPT-5.5 | 75 |
| 4 | Gemini 3.5 Flash | 75 |
| 5 | Qwen 3.6 Plus | 66.7 |
| 6 | GPT-5.4 (Medium) | 63.9 |
| 7 | GPT-5.4 | 61.1 |
| 8 | Qwen 3.5 397B A17B | 61.1 |
| 9 | Gemini 3 Pro | 58.3 |
| 10 | GPT-5.4 Mini (Medium) | 55.6 |
| 11 | GPT-5.2 (Medium) | 55.6 |
| 12 | Gemini 2.5 Pro | 52.8 |
| 13 | qwen3.5-flash | 52.8 |
| 14 | Qwen 3.5 Plus | 52.8 |
| 15 | Qwen 3.6 35B A3B | 50 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-reasoning-match-process · How the rankings work · Data refreshed daily, snapshot 2026-07-22.