command-a-reasoning-08-2025: benchmark results
Cohere's open-weights Command A Reasoning release (August 2025). Provider: Cohere. Released 2025-08-21. Access: Open.
Aggregate Rating 1641 ± 27, rank #329 of 1656 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| RewardBench 2 Math | 86.89 | Score (%) | 90.7 |
| K-MetBench | 77.8 | Accuracy (imported) | 87.9 |
| RewardBench 2 Precise IF | 45 | Score (%) | 81.5 |
| RewardBench 2 Safety | 88.61 | Score (%) | 79 |
| RewardBench 2 Focus | 88.94 | Score (%) | 76.6 |
| JudgeBench Math | 87.5 | Accuracy (%) | 46.1 |
| JudgeBench Coding | 89.29 | Accuracy (%) | 44.1 |
| RewardBench 2 Factuality | 65.63 | Accuracy (%) | 40.9 |
| JudgeBench Reasoning | 84.69 | Accuracy (%) | 37.3 |
| GSM-MC | 97.95 | Accuracy (%) | 36.6 |
| JudgeBench Knowledge | 71.1 | Accuracy (%) | 35.3 |
| MATH-MC Level 1 | 96.05 | Accuracy (%) | 30.1 |
Interactive version: theaggregate.ai/model?slug=command-a-reasoning-08-2025 · How It Works · Data refreshed daily, snapshot 2026-10-20.