AGI-Eval Community - Cognition (Chinese): leaderboard
Metric: Accuracy (%). Source: agi-eval.cn. 139 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 | 89.64 |
| 2 | Gemini 3 Pro (Preview) | 89.11 |
| 3 | Gemini 3.1 Pro (Preview) | 88.9 |
| 4 | GPT-5.5 | 88 |
| 5 | Gemini 3.5 Flash | 87.85 |
| 6 | Qwen 3.7 Max | 87.09 |
| 7 | Claude Opus 4.6 | 87.08 |
| 8 | Claude Opus 4.8 | 86.87 |
| 9 | Kimi K3 | 86.83 |
| 10 | Gemini 3 Flash (Preview) | 86.8 |
| 11 | Claude Opus 4.5 (Non-reasoning) | 85.4 |
| 12 | Seed 2.1 Pro | 85.2 |
| 13 | Grok 4 | 84.86 |
| 14 | Kimi K2.6 | 84.24 |
| 15 | GPT-5.4 | 84.12 |
Interactive version: theaggregate.ai/benchmark?slug=agi-eval-community-cognition-chinese · How It Works · Data refreshed daily, snapshot 2026-09-19.