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

AGI-Eval Community private-set Base Language Models evaluation (Interaction (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
1Qwen2.5-72B-Base81.88
2Qwen 2.5 32B (Base)81.57
3Kimi K2 Base80.87#939
4DeepSeek-V3.1-Base80.45
5DeepSeek V3 Base80.15
6ERNIE-4.5-300B-A47B-Base79.16
7Qwen2.5-14B-Base79.14
8DeepSeek-V3.2-Exp-Base79.1
9GLM-4.5-Base78.85
10Llama 4 Maverick Base78.33
11Qwen3-8B-Base77.77#1754
12Llama 3.1 405B Base77.46
13GLM4-9B-Base77.44
14Qwen3-14B-Base77.3#1473
15Llama 3.1 70B Base75.9

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