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

AGI-Eval Community private-set Base Language Models evaluation (Cognition (English)) 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
1DeepSeek-V3.1-Base85.69
2DeepSeek V3 Base84.83
3GLM-4.5-Base83.18
4DeepSeek-V3.2-Exp-Base83
5Kimi K2 Base82.75#939
6Qwen 2.5 32B (Base)81.85
7Qwen2.5-72B-Base79.46
8Qwen3-30B-A3B-Base78.89#1475
9Llama 4 Maverick Base77.82
10Llama 3.1 405B Base77.33
11Qwen3-14B-Base77.29#1473
12Qwen2.5-14B-Base77.27
13GLM4-9B-Base75.8
14Llama 3.1 70B Base75.69
15ERNIE-4.5-300B-A47B-Base75.27

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-english · How It Works · Data refreshed daily, snapshot 2026-11-22.