AGORA - Education: leaderboard
Metric: Accuracy (%) on the 49 education, science and academia questions (152 documents), archive-grounded agentic document reasoning with verifiable numeric answers over the domain collection of Markdown workplace documents, agent in the mini-swe-agent harness (bash tool only), temperature 1.0 with reasoning effort at the maximum each model supports; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 59.18 |
| 2 | GPT-5.5 (xHigh) | 48.98 |
| 3 | DeepSeek V4 Flash (Max) | 46.94 |
| 4 | DeepSeek V4 Pro (Max) | 38.78 |
| 5 | GLM-5.1 | 34.69 |
| 6 | Qwen 3.5 35B A3B | 12.24 |
| 7 | Gemini 3.1 Flash Lite (High) | 10.2 |
| 8 | Qwen 3.5 9B | 2.04 |
Interactive version: theaggregate.ai/benchmark?slug=agora-education · How It Works · Data refreshed daily, snapshot 2026-09-29.