AI for Education Visual Reasoning - reasoning by analogy — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 64 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 88.8 |
| 2 | GPT-5.6 Sol | 86.5 |
| 3 | GPT-5.4 (Medium) | 81.4 |
| 4 | Gemini 3 Flash | 80.9 |
| 5 | Qwen 3.5 397B A17B | 80 |
| 6 | Gemini 3 Pro | 79.1 |
| 7 | GPT-5.5 | 78.1 |
| 8 | Qwen 3.5 Plus | 78.1 |
| 9 | Qwen 3.6 Plus | 75.8 |
| 10 | GPT-5.2 (Medium) | 72.1 |
| 11 | Qwen 3.6 27B | 68.8 |
| 12 | Qwen 3.6 35B A3B | 67.4 |
| 13 | GPT-5.4 Mini (Medium) | 67 |
| 14 | Kimi K2.5 | 62.8 |
| 15 | qwen3.5-flash | 59.5 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-reasoning-reasoning-by-analogy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.