CorpusQA (1M) - Education: leaderboard
Metric: Accuracy (%; 82 questions over English education documents, 1M-token corpora, DeepSeek-V3 judge). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 65.85 |
| 2 | Gemini 2.5 Flash | 48.78 |
| 3 | MiniMax M1 80k | 7.32 |
Interactive version: theaggregate.ai/benchmark?slug=corpusqa-1m-education · How It Works · Data refreshed daily, snapshot 2026-09-25.