SpecialEduBench - Knowledge: leaderboard
Metric: Macro-average accuracy over four knowledge categories (%; exact match on four-option items: 3,752 medical items from MedMCQA and MedQA, 500 generated early-milieu-teaching items, 223 special-educational-needs items from the Pedagogy Benchmark and 62 psychology items from MMLU and MMLU-Pro; mean of three runs at temperature 1.0; text only). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (Low) | 93.7 |
| 2 | Gemini 3.1 Pro (Preview) | 93.6 |
| 3 | Grok 4.5 | 92.1 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 87.8 |
| 5 | Mistral Large 3 | 85.2 |
Interactive version: theaggregate.ai/benchmark?slug=specialedubench-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-26.