Open Arabic LLM - Arabic MMLU HT High School Microeconomics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 163 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 84.45 |
| 2 | calme-2.1-qwen2.5-72B | 84.45 |
| 3 | calme-2.2-qwen2.5-72B | 84.45 |
| 4 | Ultiima-72B | 84.45 |
| 5 | Rombos-LLM-V2.5-Qwen-72B | 84.03 |
| 6 | Qwen 2 72B | 78.15 |
| 7 | Gemma 3 27B (IT) | 74.79 |
| 8 | gemma-3-27B-pt | 74.79 |
| 9 | Qwen 2.5 72B | 74.37 |
| 10 | Qwen 2.5 32B Instruct | 73.53 |
| 11 | Qwentile2.5-32B-Instruct | 73.53 |
| 12 | lambda-qwen2.5-32B-dpo-test | 73.11 |
| 13 | Qwen3-8B-Base | 72.27 |
| 14 | Awqward2.5-32B-Instruct | 72.27 |
| 15 | Qwen2.5-32B-Instruct-abliterated-v2 | 71.85 |
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-arabic-mmlu-ht-high-school-microeconomics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.