Open Arabic LLM - Arabic MMLU HT High School Macroeconomics: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 163 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 81.77 |
| 2 | Qwen 2 72B | 78.38 |
| 3 | Llama 3.3 70B Instruct | 76.55 |
| 4 | Qwen 2.5 72B | 76.37 |
| 5 | gemma-3-27B-pt | 75.41 |
| 6 | Gemma 3 27B (IT) | 74.75 |
| 7 | Qwen 2.5 32B Instruct | 74.09 |
| 8 | Qwen2.5-32B-Instruct-CFT | 73.95 |
| 9 | Awqward2.5-32B-Instruct | 73.82 |
| 10 | Qwentile2.5-32B-Instruct | 73.4 |
| 11 | Qwen2.5-32B-Instruct-abliterated-v2 | 72.95 |
| 12 | EZO-Qwen2.5-32B-Instruct | 69.6 |
| 13 | Saka-14B | 69.18 |
| 14 | aya-expanse-32B | 68.9 |
| 15 | Gemma 2 27B (IT) | 68.66 |
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-arabic-mmlu-ht-high-school-macroeconomics · How It Works · Data refreshed daily, snapshot 2026-09-05.