AGI-Eval Community - Subject Knowledge: 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 subject knowledge dimension; upstream's Chinese split is identical, so only this column is kept. Upstream accuracy 0-1, shown as 0-100; higher is better.
Metric: Accuracy (%). Source: agi-eval.cn. Saturation forecast: Estimated already saturated. 141 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed 2.0 Pro | 91.1 | #122 |
| 2 | Qwen 3.7 Max | 90.83 | #85 |
| 3 | Seed 2.1 Pro | 90.75 | #73 |
| 4 | Gemini 3.1 Pro (Preview) | 90.32 | #64 |
| 5 | Gemini 3.5 Flash | 90.25 | #66 |
| 6 | Hy3 | 89.91 | #100 |
| 7 | Claude Fable 5 | 89.75 | #20 |
| 8 | Kimi K2.6 | 89.59 | #113 |
| 9 | DeepSeek V4 Pro (Max) | 89.52 | #112 (DeepSeek V4 Pro) |
| 10 | Gemini 3 Pro (Preview) | 89.51 | #71 |
| 11 | GPT-5.5 | 89.41 | #33 |
| 12 | GLM-5.2 | 89.32 | #80 |
| 13 | GLM-5.1 | 89.17 | #109 |
| 14 | Kimi K2.5 (Thinking) | 88.86 | #152 (Kimi K2.5) |
| 15 | Kimi K3 | 88.82 | #35 |
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-subject-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-05.