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

AGI-Eval Community private-set Base Language Models evaluation (Coding 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 Base39.95#939
2Qwen3-30B-A3B-Base33.01#1475
3ERNIE-4.5-300B-A47B-Base28.78
4Qwen3-14B-Base26.72#1473
5Llama 3.1 405B Base23.13
6GLM-4.5-Base21.01
7Qwen3-8B-Base20.75#1754
8Llama 4 Maverick Base20.45
9DeepSeek-V3.2-Exp-Base18.16
10Qwen2.5-72B-Base18.1
11Qwen 2.5 32B (Base)17.72
12Qwen3-4B-Base16.93#2439
13DeepSeek-V3.1-Base15.67
14Qwen2.5-14B-Base15.23
15Gemma-3-27B-Base14.95

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