AI for Education Pedagogy - Maths — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 223 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 | 94.44 |
| 2 | Gemini 3 Pro | 93.65 |
| 3 | GPT-5.6 Sol | 92.86 |
| 4 | Claude Sonnet 4.5 (Thinking) | 92.06 |
| 5 | Gemini 3.5 Flash | 92.06 |
| 6 | Qwen 3.7 Max | 92.06 |
| 7 | GPT-5.4 (Medium) | 92.06 |
| 8 | GPT-5.5 | 91.27 |
| 9 | Qwen 3.6 Max Preview | 91.27 |
| 10 | Claude Opus 4.7 | 90.48 |
| 11 | Kimi K2.6 | 90.48 |
| 12 | Grok 4.5 | 90.48 |
| 13 | Qwen 3.5 Plus | 90.48 |
| 14 | Gemini 2.5 Pro | 89.68 |
| 15 | Claude Opus 4.8 | 89.68 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-pedagogy-maths · How the rankings work · Data refreshed daily, snapshot 2026-07-22.