Arabic.AI LLM-S: benchmark results
Provider: Other.
Aggregate Rating 1644 ± 40, rank #661 of 10916 rated models, from 133 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Arabic - Arabic Mmlu - Civics (High School) | 75.86 | Exact Match (%) | 97.5 |
| HELM Arabic - Mbzuai Human Translated Arabic Mmlu - Virology | 75.9 | Exact Match (%) | 97.5 |
| HELM Arabic - Arabic Exams - Biology | 68.57 | Exact Match (%) | 96.2 |
| HELM Arabic - Alghafa - MCQ Exams Test AR | 77.92 | Exact Match (%) | 95 |
| HELM Arabic - Alghafa - Multiple Choice Rating Sentiment Task | 79.3 | Exact Match (%) | 95 |
| HELM Arabic - Alghafa - Multiple Choice Sentiment Task | 75.8 | Exact Match (%) | 95 |
| HELM Arabic - Alrage | 93.03 | Score | 95 |
| HELM Arabic - Arabic Mmlu - Arabic Language (High School) | 91.03 | Exact Match (%) | 95 |
| HELM Arabic - Arabic Mmlu - Civics (Middle School) | 78.81 | Exact Match (%) | 95 |
| HELM Arabic - Arabic Mmlu - Geography (High School) | 81.5 | Exact Match (%) | 95 |
| HELM Arabic - Arabic Mmlu - Geography (Middle School) | 86.76 | Exact Match (%) | 95 |
| HELM Arabic - Arabic Mmlu - History (High School) | 80.79 | Exact Match (%) | 95 |
Interactive version: theaggregate.ai/model?slug=arabic-ai-llm-s · How It Works · Data refreshed daily, snapshot 2026-11-08.