c4ai-command-r7B-arabic-02-2025: benchmark results
Provider: Cohere. Released 2025-02-27. Access: Open.
Unified ELO 1559 ± 24, rank #800 of 2656 rated models, from 151 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment Task | 58.33 | Accuracy (%) | 98.8 |
| Open Arabic LLM - Arabic Exams | 64.99 | Accuracy (%) | 98.8 |
| Open Arabic LLM - Arabic MMLU Social Science (Middle School) | 63.49 | Accuracy (%) | 98.8 |
| Open Arabic LLM - Alghafa Multiple Choice Facts Truefalse Balanced Task | 96 | Accuracy (%) | 97.2 |
| Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment NO Neutral Task | 81.74 | Accuracy (%) | 92 |
| QIMMA - FannOrFlop | 58.55 | F1 (%) | 87.8 |
| Open Arabic LLM - Arabic MMLU Computer Science (Middle School) | 92.59 | Accuracy (%) | 87 |
| Open Arabic LLM - Arabic MMLU Arabic Language (Grammar) | 53.42 | Accuracy (%) | 84.6 |
| QIMMA - MizanQA | 59.98 | Normalized multiple-choice probability score (%) | 82.9 |
| Open Arabic LLM - Madinah QA Arabic Language (Grammar) | 55.62 | Accuracy (%) | 82.4 |
| Open Arabic LLM - Madinah QA Average | 63.84 | Accuracy (%) | 81.5 |
| QIMMA - ArabCulture | 66.94 | Accuracy (%, log-likelihood multiple choice) | 80.5 |
Interactive version: theaggregate.ai/model?slug=c4ai-command-r7b-arabic-02-2025 · How It Works · Data refreshed daily, snapshot 2026-09-19.