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

AGI-Eval Community private-set Base Language Models evaluation (General Reasoning (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
1ERNIE-4.5-300B-A47B-Base87.74
2DeepSeek-V3.1-Base86.58
3DeepSeek V3 Base86.4
4Kimi K2 Base86.33#939
5DeepSeek-V3.2-Exp-Base84.17
6GLM-4.5-Base84.12
7Llama 4 Maverick Base84.07
8Llama 3.1 405B Base83.4
9Qwen2.5-72B-Base83.12
10Qwen 2.5 32B (Base)81.99
11Qwen3-14B-Base81.5#1473
12Qwen3-30B-A3B-Base77.92#1475
13Llama 3.1 70B Base76.54
14Qwen2.5-14B-Base76.52
15Qwen3-8B-Base75.41#1754

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