AGI-Eval Community - Learning (English): leaderboard
Metric: Accuracy (%). Source: agi-eval.cn. 139 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 97.52 |
| 2 | Gemini 3 Flash (Preview) | 97.31 |
| 3 | Qwen 3.7 Max | 96.94 |
| 4 | GPT-5.4 | 96.72 |
| 5 | Seed 2.0 Pro | 96.54 |
| 6 | Kimi K2.6 | 96.41 |
| 7 | Kimi K3 | 96.41 |
| 8 | GLM-5.2 | 96.38 |
| 9 | Gemini 3.5 Flash | 96.34 |
| 10 | GLM-5.1 | 96.09 |
| 11 | GPT-5.5 | 96 |
| 12 | DeepSeek V4 Pro (Max) | 95.91 |
| 13 | Gemini 3 Pro (Preview) | 95.77 |
| 14 | GPT-5.1 | 95.56 |
| 15 | Qwen 3.5 397B A17B (Thinking) | 95.38 |
Interactive version: theaggregate.ai/benchmark?slug=agi-eval-community-learning-english · How It Works · Data refreshed daily, snapshot 2026-09-19.