Command-R+: benchmark results
Cohere Command R+ model, a higher-capacity Command R variant for retrieval, tool use, and complex enterprise tasks. Provider: Cohere. Released 2024-04-04. Access: Open.
Aggregate Rating 1469 ± 9, rank #891 of 1656 rated models, from 648 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Language - Content Summarization - English (CompassBench 2405) | 42.7 | Score (%) | 100 |
| OpenCompass Language - Content Summarization - Chinese (CompassBench 2405) | 27.6 | Score (%) | 94.7 |
| BALSAM - Text Manipulation | 64.69 | Overall score (0-100, LLM-judged generation and multiple cho | 92.6 |
| HELM Lite - LegalBench - Corporate Lobbying | 84.29 | Exact Match (%) | 90 |
| OpenCompass LLM - Agent - Chinese (CompassBench 2405) | 72.7 | Score (%) | 86.8 |
| HELM Safety - Simple Safety Tests | 100 | LM Evaluated Safety score | 86 |
| CRM LLM Leaderboard | 66.2 | CRM Accuracy (0-100) | 85.3 |
| BALSAM - Reading Comprehension | 58.16 | Overall score (0-100, LLM-judged generation and multiple cho | 85.2 |
| OpenCompass LLM - Knowledge - English (CompassBench 2405) | 81.2 | Score (%) | 84.2 |
| OpenCompass Language - Sentiment Analysis - English (CompassBench 2405) | 79.3 | Score (%) | 84.2 |
| OpenCompass Subjective - Knowledge - English (CompassBench 2405) | 49.6 | Score (%) | 84.2 |
| OpenCompass Math - College - English (CompassBench 2405) | 31.6 | Score (%) | 82.9 |
Interactive version: theaggregate.ai/model?slug=command-r-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.