AGI-Eval Community Base - Cognition (Chinese): leaderboard

AGI-Eval Community private-set Base Language Models evaluation (Cognition (Chinese)) measuring accuracy (%) across bilingual capability dimensions.

Metric: Accuracy (%). Source: agi-eval.org. Saturation forecast: Estimated already saturated. 25 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Kimi K2 Base87.89#939
2DeepSeek-V3.1-Base86.37
3DeepSeek-V3.2-Exp-Base85.79
4Llama 3.1 405B Base85.51
5DeepSeek V3 Base85.44
6Llama 4 Maverick Base84.51
7Llama 3.1 70B Base83.77
8GLM-4.5-Base82.99
9Qwen 2.5 32B (Base)80.93
10Gemma-3-27B-Base77.9
11Llama 4 Scout Base75.88#1967
12GLM4-9B-Base75.8
13Qwen3-30B-A3B-Base74.07#1475
14Qwen2.5-72B-Base73.97
15ERNIE-4.5-300B-A47B-Base73.28

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=agi-eval-community-base-cognition-chinese · How It Works · Data refreshed daily, snapshot 2026-11-22.