SAGE — leaderboard
SAGE evaluates model capability on education tasks from the linked upstream source with Score as the primary reported metric.
Metric: OA (%) (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 74.17 |
| 2 | Qwen 3.5 35B A3B | 71.79 |
| 3 | Llama 3.1 70B | 71.54 |
| 4 | Qwen 3.5 9B | 66.21 |
| 5 | Gemma 3 27B | 66.17 |
| 6 | Llama 3.1 8B | 64.71 |
| 7 | Gemma 3 12B | 64.5 |
| 8 | Gemma 3 4B | 60.79 |
| 9 | Qwen 3.5 4B | 60.5 |
| 10 | Llama 3.2 3B | 59.54 |
| 11 | Qwen 3.5 2B | 54.12 |
| 12 | Llama 3.2 1B | 53.67 |
Interactive version: theaggregate.ai/benchmark?slug=sage · How the rankings work · Data refreshed daily, snapshot 2026-07-22.