AI for Education Visual Maths - Algebra: leaderboard
This is the algebra slice of Fab AI's Visual Maths Benchmark, a set of 237 early grade maths questions that each depend on an image, selected from the Math-Vision (Math-V) dataset. It scores only the algebra strand, as the percent of questions answered correctly, where higher is better. Source: benchmarks.ai-for-education.org/leaderboards/maths.
Metric: Accuracy (%). Source: www.fab-ai.org. Saturation forecast: Estimated already saturated. 76 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 100 | #152 |
| 2 | GPT-5.5 | 96.15 | #31 |
| 3 | Gemini 3 Pro | 96.15 | #80 |
| 4 | GPT-5.6 Sol | 96.15 | #19 |
| 5 | Qwen 3.6 Plus | 96.15 | #120 |
| 6 | Claude Opus 5 | 96.15 | #12 |
| 7 | GPT-5 (Medium) | 96.15 | #98 (GPT-5) |
| 8 | GPT-5.4 (Medium) | 96.15 | #79 (GPT-5.4) |
| 9 | Gemini 3.1 Pro (Preview) | 92.31 | #58 |
| 10 | Claude Sonnet 4.6 | 92.31 | #90 |
| 11 | Gemini 3 Flash | 92.31 | #99 |
| 12 | O3 | 92.31 | #124 |
| 13 | Qwen 3.6 35B A3B | 92.31 | #226 |
| 14 | Qwen 3.5 Plus | 92.31 | #125 |
| 15 | Claude Fable 5 | 92.31 | #16 |
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-maths-algebra · How It Works · Data refreshed daily, snapshot 2026-10-20.