AGI-Eval Community Base - General Reasoning (Chinese): leaderboard

AGI-Eval Community private-set Base Language Models evaluation (General Reasoning (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
1GLM-4.5-Base95.45
2Kimi K2 Base90.91#939
3ERNIE-4.5-300B-A47B-Base90.91
4DeepSeek-V3.2-Exp-Base81.82
5Qwen3-14B-Base77.27#1473
6DeepSeek-V3.1-Base77.27
7Qwen3-8B-Base72.73#1754
8Qwen3-30B-A3B-Base72.73#1475
9DeepSeek V3 Base72.73
10Qwen 2.5 32B (Base)72.73
11Qwen2.5-72B-Base72.73
12Qwen2.5-14B-Base72.73
13Llama 3.1 405B Base68.18
14Llama 4 Maverick Base63.64
15Qwen 2.5 7B (Base)63.64

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