AI for Education SEND — leaderboard
Metric: Accuracy (%). Source: www.fab-ai.org. 215 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 88.07 |
| 2 | GPT-5.6 Sol | 87.61 |
| 3 | Claude Fable 5 | 87.16 |
| 4 | Gemini 3.5 Flash | 86.24 |
| 5 | Gemini 2.5 Pro | 85.78 |
| 6 | Gemini 3 Flash | 85.78 |
| 7 | Claude Opus 4.7 | 85.32 |
| 8 | Qwen 3.7 Max | 85.32 |
| 9 | Grok 4.5 | 84.86 |
| 10 | Gemini 3 Pro | 84.4 |
| 11 | Grok 4.20 (Reasoning) | 83.94 |
| 12 | GPT-5.4 (Medium) | 83.94 |
| 13 | Claude Sonnet 4.5 (Thinking) | 83.49 |
| 14 | Qwen 3.5 397B A17B | 83.49 |
| 15 | Claude Opus 4.8 | 83.03 |
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-send · How the rankings work · Data refreshed daily, snapshot 2026-07-22.