c4ai-command-r7B-12-2024: benchmark results
Cohere's smallest Command R (7B) with a 128K context, open weights tuned for RAG, tool use, and agents. Provider: Cohere. Released 2024-12-13. Access: Open.
Aggregate Rating 1417 ± 16, rank #1161 of 1656 rated models, from 155 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 77.13 | Score | 93.1 |
| Open LLM Leaderboard - MATH Level 5 | 29.91 | Score | 81.8 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 47.95 | Matthews correlation coefficient (%) | 80.8 |
| Open PL LLM - PPC (multiple choice, 5-shot) | 78.2 | Accuracy (%) | 80.5 |
| Arabic IFEval | 60.8 | Arabic Accuracy (%) | 79.5 |
| EuroEval Spanish NLU | 50.76 | NLU Average Score (%) | 77.3 |
| EuroEval Spanish NLU - MLQA ES | 64.05 | Character F1 (%) | 75.9 |
| QIMMA - ArabCulture | 62.78 | Accuracy (%, log-likelihood multiple choice) | 75.6 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 81.48 | Binary F1 (%) | 74 |
| Open LLM Leaderboard - BBH | 55.03 | Score | 73.6 |
| Open PL LLM - EQ-Bench | 45.76 | EQ-Bench Score | 72.8 |
| EuroEval Portuguese NLU - HAREM | 48.11 | Micro F1 excluding MISC (%) | 71.7 |
Interactive version: theaggregate.ai/model?slug=c4ai-command-r7b-12-2024 · How It Works · Data refreshed daily, snapshot 2026-10-20.