AI for Education Pedagogy - Technology: leaderboard
The technology slice of the pedagogy exam set: four-option multiple-choice questions on teaching and assessing that subject, drawn from Chilean teacher qualification exams and translated into English. Items are answered closed-book in a single turn and scored by exact match on the answer letter. Higher is better. Source: arxiv.org/abs/2506.18710.
Metric: Accuracy (%). Source: www.fab-ai.org. Saturation forecast: Around January 2027. 249 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 91.51 | #12 |
| 2 | Claude Fable 5.1 | 90.57 | #9 |
| 3 | Kimi K2.5 | 89.62 | #144 |
| 4 | Qwen 3.5 27B | 88.68 | #187 |
| 5 | GPT-5.6 Sol | 88.68 | #19 |
| 6 | Grok 4.3 | 88.68 | #188 |
| 7 | GPT-5.2 (Medium) | 88.68 | #110 (GPT-5.2) |
| 8 | Gemini 2.5 Pro | 87.74 | #152 |
| 9 | Gemini 3.1 Pro (Preview) | 87.74 | #58 |
| 10 | Gemini 3 Flash | 87.74 | #99 |
| 11 | Kimi K2.6 | 87.74 | #104 |
| 12 | Claude Opus 4.8 | 87.74 | #37 |
| 13 | Claude Sonnet 4.5 (Thinking) | 87.74 | #142 (Claude Sonnet 4.5) |
| 14 | Qwen 3.7 Max | 87.74 | #75 |
| 15 | Claude Fable 5 | 87.74 | #16 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=ai-for-education-pedagogy-technology · How It Works · Data refreshed daily, snapshot 2026-10-20.