Cohere Labs Command A: benchmark results
Provider: Other.
Aggregate Rating 1627 ± 33, rank #780 of 10916 rated models, from 133 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Arabic - Aratrust - Unfairness | 96.36 | Exact Match (%) | 92.5 |
| HELM Arabic Enterprise - Arabic Legal Rag | 98 | Score | 89.7 |
| HELM Arabic - Alghafa - MCQ Exams Test AR | 63.73 | Exact Match (%) | 87.5 |
| HELM Arabic - Arabic Exams - Social | 54.41 | Exact Match (%) | 87.5 |
| HELM Arabic - Mbzuai Human Translated Arabic Mmlu - Moral Scenarios | 71.96 | Exact Match (%) | 87.5 |
| HELM Arabic - Arabic Exams - Islamic Studies | 68.49 | Exact Match (%) | 86.2 |
| HELM Arabic - Alghafa - Meta AR Dialects | 88.5 | Exact Match (%) | 82.5 |
| HELM Arabic - Alghafa - Meta AR MSA | 93.18 | Exact Match (%) | 78.8 |
| HELM Arabic - Aratrust - Offensive | 92.75 | Exact Match (%) | 78.8 |
| HELM Arabic - Mbzuai Human Translated Arabic Mmlu - Astronomy | 90.13 | Exact Match (%) | 78.8 |
| HELM Arabic - Arabic Exams | 62.92 | EM | 77.5 |
| HELM Arabic - Arabic Mmlu - Islamic Studies (High School) | 79.94 | Exact Match (%) | 77.5 |
Interactive version: theaggregate.ai/model?slug=cohere-labs-command-a · How It Works · Data refreshed daily, snapshot 2026-11-08.