Open Arabic LLM - Alghafa Multiple Choice Facts Truefalse Balanced Task — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 163 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | aya-expanse-32B | 98.67 |
| 2 | Qwen 2 72B | 96 |
| 3 | Qwen 3 8B | 94.67 |
| 4 | Qwen2.5-32B-Instruct-abliterated-v2 | 94.67 |
| 5 | Qwen3-8B-Base | 93.33 |
| 6 | recoilme-gemma-2-9B-v0.2 | 93.33 |
| 7 | Gemma 3 27B (IT) | 92 |
| 8 | Gemma 2 27B (IT) | 92 |
| 9 | gemma-3-27B-pt | 92 |
| 10 | aya-23-35B | 92 |
| 11 | Qwen 2.5 72B | 92 |
| 12 | free-evo-qwen72B-v0.8-re | 92 |
| 13 | T.E-8.1 | 92 |
| 14 | Qwen 2.5 72B Instruct | 90.67 |
| 15 | Qwen 2.5 32B Instruct | 90.67 |
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-alghafa-multiple-choice-facts-truefalse-balanced-task · How the rankings work · Data refreshed daily, snapshot 2026-07-22.