CorpusQA (128K) - Education: leaderboard
Metric: Accuracy (%; 82 questions over English education documents, 128K-token corpora, DeepSeek-V3 judge). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 81.71 |
| 2 | DeepSeek R1 0528 | 78.05 |
| 3 | Gemini 2.5 Pro | 76.83 |
| 4 | MiniMax M1 80k | 76.83 |
| 5 | Gemini 2.5 Flash | 74.39 |
| 6 | GPT-5 Mini | 74.39 |
| 7 | Qwen 3 235B A22B 2507 (Thinking) | 70.73 |
| 8 | Qwen 3 30B A3B 2507 (Thinking) | 64.63 |
Interactive version: theaggregate.ai/benchmark?slug=corpusqa-128k-education · How It Works · Data refreshed daily, snapshot 2026-09-25.