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

AGI-Eval Community private-set Base Language Models evaluation (Mathematical 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
1Kimi K2 Base71.43#939
2ERNIE-4.5-300B-A47B-Base71.02
3DeepSeek-V3.2-Exp-Base60.13
4DeepSeek-V3.1-Base58.52
5GLM-4.5-Base58.24
6Qwen3-30B-A3B-Base57.09#1475
7Llama 4 Maverick Base56.93
8DeepSeek V3 Base55.6
9Qwen2.5-72B-Base54.74
10Qwen3-14B-Base53.63#1473
11Qwen 2.5 32B (Base)53.36
12Qwen3-8B-Base49.67#1754
13Qwen2.5-14B-Base46.77
14Qwen3-4B-Base45.1#2439
15Qwen 2.5 7B (Base)42.79

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