Open Arabic LLM - Arabic MMLU HT Security Studies — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 163 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 27B (IT) | 76.73 |
| 2 | Saka-14B | 75.1 |
| 3 | tempmotacilla-cinerea-0308 | 73.06 |
| 4 | calme-2.1-qwen2.5-72B | 72.65 |
| 5 | free-evo-qwen72B-v0.8-re | 72.24 |
| 6 | calme-2.2-qwen2.5-72B | 72.24 |
| 7 | Rombos-LLM-V2.5-Qwen-72B | 72.24 |
| 8 | Ultiima-72B | 72.24 |
| 9 | Qwentile2.5-32B-Instruct | 71.84 |
| 10 | Qwen2.5-32B-Instruct-abliterated-v2 | 71.43 |
| 11 | Qwen 2.5 32B Instruct | 70.61 |
| 12 | Awqward2.5-32B-Instruct | 70.61 |
| 13 | Qwen2.5-32B-Instruct-CFT | 70.2 |
| 14 | Qwen 2.5 72B Instruct | 69.8 |
| 15 | gemma-3-27B-pt | 69.39 |
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-arabic-mmlu-ht-security-studies · How the rankings work · Data refreshed daily, snapshot 2026-07-22.