AGI-Eval Community Base - Interaction (English): leaderboard
AGI-Eval Community private-set Base Language Models evaluation (Interaction (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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-72B-Base | 73.43 | |
| 2 | Llama 3.1 405B Base | 73.18 | |
| 3 | DeepSeek-V3.1-Base | 73.13 | |
| 4 | Qwen3-14B-Base | 72.38 | #1473 |
| 5 | Qwen 2.5 32B (Base) | 71.68 | |
| 6 | DeepSeek V3 Base | 71.3 | |
| 7 | DeepSeek-V3.2-Exp-Base | 70.07 | |
| 8 | GLM4-9B-Base | 68.67 | |
| 9 | ERNIE-4.5-300B-A47B-Base | 68.34 | |
| 10 | Kimi K2 Base | 67.71 | #939 |
| 11 | Gemma-3-12B-Base | 67.18 | |
| 12 | Qwen2.5-14B-Base | 66.69 | |
| 13 | Qwen3-8B-Base | 66.23 | #1754 |
| 14 | Qwen 2.5 7B (Base) | 66.2 | |
| 15 | Gemma-3-4B-Base | 65.94 |
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-english · How It Works · Data refreshed daily, snapshot 2026-11-22.