Open Arabic LLM - Arabic MMLU LAW (Professional): leaderboard
The "Arabic MMLU LAW (Professional)" subtask of Open Arabic LLM. A task from the Open Arabic LLM Leaderboard, evaluating models on Arabic-language knowledge, reasoning and understanding across native and translated benchmarks.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Not forecast. 163 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Saka-14B | 79.62 | #344 |
| 2 | Qwen 2 72B | 78.66 | #521 |
| 3 | Qwen 2.5 72B Instruct | 78.03 | #454 |
| 4 | Hala-9B | 77.71 | #504 |
| 5 | Qwen2.5-32B-Instruct-abliterated-v2 | 76.75 | #394 |
| 6 | gemma-3-4B-pt Base | 75.8 | #1134 |
| 7 | gemma-3-27B-pt | 75.8 | #502 |
| 8 | Fanar-1-9B | 75.8 | #778 |
| 9 | AIC-1 | 75.48 | #231 |
| 10 | Qwen 2.5 14B | 75.16 | #725 |
| 11 | Qwen 2.5 7B | 74.84 | #922 |
| 12 | aya-23-35B | 74.84 | #883 |
| 13 | jais-adapted-70B-chat | 74.84 | #636 |
| 14 | ALLaM-7B-Instruct-preview | 74.2 | #718 |
| 15 | Yehia-7B-preview | 74.2 | #646 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-arabic-mmlu-law-professional · How It Works · Data refreshed daily, snapshot 2026-10-20.