c4ai-command-r-08-2024: benchmark results
CohereForAI Command R August 2024 open-weight checkpoint. Provider: Cohere. Released 2024-08-30. Access: Open.
Aggregate Rating 1463 ± 16, rank #921 of 1656 rated models, from 160 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenCzechMark - Sentiment | 81.82 | Duel Win Score (%) | 96.1 |
| Open Portuguese LLM - OAB Exams | 59.59 | Accuracy (%) | 91.9 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 49.76 | Matthews correlation coefficient (%) | 90.5 |
| EuroEval Italian NLU - MultiNERD IT | 80.1 | Micro F1 excluding MISC (%) | 90.4 |
| Open Portuguese LLM - ENEM | 76.49 | Accuracy (%) | 90.1 |
| Open Portuguese LLM - ASSIN2 RTE | 93.3 | Macro F1 (%) | 88.4 |
| EuroEval French NLU - Eltec | 69.56 | Micro F1 excluding MISC (%) | 88 |
| EuroEval Portuguese NLU - HAREM | 54.2 | Micro F1 excluding MISC (%) | 87.3 |
| Open Portuguese LLM - BLUEX | 65.37 | Accuracy (%) | 86.5 |
| EuroEval Portuguese NLU - SST-2 PT | 83.72 | Matthews correlation coefficient (%) | 85.9 |
| EuroEval Italian NLU - SQuAD IT | 72.56 | Character F1 (%) | 85.7 |
| EuroEval Portuguese NLU | 58.4 | NLU Average Score (%) | 85.7 |
Interactive version: theaggregate.ai/model?slug=c4ai-command-r-08-2024 · How It Works · Data refreshed daily, snapshot 2026-10-20.