Open Arabic LLM - Arabic MMLU History (Primary School): leaderboard
Metric: Accuracy (%). Source: huggingface.co. 163 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 75.49 |
| 2 | EZO-Qwen2.5-32B-Instruct | 72.55 |
| 3 | Qwen2.5-32B-Instruct-CFT | 71.57 |
| 4 | Qwen 2.5 32B Instruct | 70.59 |
| 5 | Qwen 2.5 72B | 70.59 |
| 6 | Awqward2.5-32B-Instruct | 70.59 |
| 7 | tempmotacilla-cinerea-0308 | 70.59 |
| 8 | gemma-3-27B-pt | 69.61 |
| 9 | Qwentile2.5-32B-Instruct | 69.61 |
| 10 | Qwen2.5-32B-Instruct-abliterated-v2 | 68.63 |
| 11 | lambda-qwen2.5-14B-dpo-test | 68.63 |
| 12 | Qwen3-8B-Base | 67.65 |
| 13 | Gemma 3 27B (IT) | 66.67 |
| 14 | Llama 3.3 70B Instruct | 66.67 |
| 15 | Qwen 2.5 14B | 66.67 |
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-arabic-mmlu-history-primary-school · How It Works · Data refreshed daily, snapshot 2026-09-05.