Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task: leaderboard
The "Alghafa Multiple Choice Grounded Statement Soqal Task" 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: Estimated already saturated. 163 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | AIC-1 | 96.67 | #237 |
| 2 | Qwen 2.5 32B Instruct | 94.67 | #511 |
| 3 | Qwentile2.5-32B-Instruct | 94.67 | #345 |
| 4 | Awqward2.5-32B-Instruct | 94.67 | #370 |
| 5 | Qwen2.5-32B-Instruct-CFT | 94.67 | #377 |
| 6 | Rombos-LLM-V2.6-Qwen-14B | 94.67 | #522 |
| 7 | lambda-qwen2.5-14B-dpo-test | 94 | #482 |
| 8 | Hala-9B | 94 | #518 |
| 9 | Qwen2.5-14B-Gutenberg-1e-Delta | 94 | #473 |
| 10 | recoilme-gemma-2-9B-v0.4 | 94 | #575 |
| 11 | Qwen 2.5 72B Instruct | 93.33 | #470 |
| 12 | Qwen 2.5 14B Instruct | 93.33 | #655 |
| 13 | AceGPT-v2-32B-Chat | 93.33 | #519 |
| 14 | Saka-14B | 93.33 | #352 |
| 15 | Qwen2.5-Lumen-14B | 93.33 | #483 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-arabic-llm-alghafa-multiple-choice-grounded-statement-soqal-task · How It Works · Data refreshed daily, snapshot 2026-11-06.