Open Arabic LLM - Arabic MMLU Political Science (University): leaderboard
The "Arabic MMLU Political Science (University)" 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: Around January 2027. 163 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 72.86 | #454 |
| 2 | AIC-1 | 71.43 | #231 |
| 3 | gemma-3-27B-pt | 70.48 | #502 |
| 4 | Saka-14B | 70 | #344 |
| 5 | Awqward2.5-32B-Instruct | 69.52 | #371 |
| 6 | Qwen2.5-32B-Instruct-CFT | 69.52 | #375 |
| 7 | Qwen2.5-32B-Instruct-abliterated-v2 | 69.05 | #394 |
| 8 | Gemma 3 27B (IT) | 68.57 | #523 |
| 9 | Qwen 2.5 32B Instruct | 68.57 | #498 |
| 10 | gemma-3-12B-pt | 68.1 | #686 |
| 11 | Qwentile2.5-32B-Instruct | 68.1 | #339 |
| 12 | Qwen 2.5 14B | 67.14 | #725 |
| 13 | Qwen 2 72B | 67.14 | #521 |
| 14 | Fanar-1-9B-Instruct | 67.14 | #633 |
| 15 | tempmotacilla-cinerea-0308 | 67.14 | #395 |
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-political-science-university · How It Works · Data refreshed daily, snapshot 2026-10-20.