AI for Education Visual Reasoning - match (figure): leaderboard
The "match (figure)" subtask of AI for Education Visual Reasoning. A task from the AI for Education benchmark measuring visual reasoning over educational diagrams, charts and figures.
Metric: Accuracy (%). Source: www.fab-ai.org. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash | 87.4 | #23 |
| 2 | Gemini 3.5 Flash | 85.2 | #60 |
| 3 | Gemini 3.6 Flash | 84.7 | #51 |
| 4 | Gemini 3.1 Pro (Preview) | 82 | #58 |
| 5 | GPT-5.6 Sol | 77 | #19 |
| 6 | Gemini 3 Flash | 76 | #99 |
| 7 | GPT-5.5 | 74.3 | #31 |
| 8 | Gemini 3 Pro | 73.8 | #80 |
| 9 | Qwen 3.5 397B A17B | 69.9 | #146 |
| 10 | GPT-5.4 (Medium) | 69.4 | #79 (GPT-5.4) |
| 11 | Qwen 3.6 Plus | 67.8 | #120 |
| 12 | Qwen 3.5 Plus | 67.2 | #125 |
| 13 | Kimi K3 | 63.9 | #30 |
| 14 | Kimi K2.5 | 63.4 | #144 |
| 15 | Gemini 2.5 Pro | 60.7 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-visual-reasoning-match-figure · How It Works · Data refreshed daily, snapshot 2026-10-20.