AGI-Eval Community - Learning (English): leaderboard
AGI-Eval community leaderboard (agi-eval.cn), the private-set LLM board built from the platform's non-public items; latest monthly snapshot. Unrelated to the AGIEval exam dataset. This board is the English-language item split (_英) of the learning column; the parent column combines both splits. Upstream accuracy 0-1, shown as 0-100; higher is better.
Metric: Accuracy (%). Source: agi-eval.cn. Saturation forecast: Estimated already saturated. 139 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 97.52 | #64 |
| 2 | Gemini 3 Flash (Preview) | 97.31 | #90 |
| 3 | Qwen 3.7 Max | 96.94 | #85 |
| 4 | GPT-5.4 | 96.72 | #83 |
| 5 | Seed 2.0 Pro | 96.54 | #122 |
| 6 | Kimi K2.6 | 96.41 | #113 |
| 7 | Kimi K3 | 96.41 | #35 |
| 8 | GLM-5.2 | 96.38 | #80 |
| 9 | Gemini 3.5 Flash | 96.34 | #66 |
| 10 | GLM-5.1 | 96.09 | #109 |
| 11 | GPT-5.5 | 96 | #33 |
| 12 | DeepSeek V4 Pro (Max) | 95.91 | #112 (DeepSeek V4 Pro) |
| 13 | Gemini 3 Pro (Preview) | 95.77 | #71 |
| 14 | GPT-5.1 | 95.56 | #145 |
| 15 | Qwen 3.5 397B A17B (Thinking) | 95.38 | #154 (Qwen 3.5 397B A17B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=agi-eval-community-learning-english · How It Works · Data refreshed daily, snapshot 2026-11-05.