c4ai-command-r-plus: benchmark results
Cohere's 104B open-weights (CC-BY-NC) model optimized for enterprise RAG with citations and multi-step tool use, with a 128K context. Provider: Cohere. Released 2024-04-04. Access: Open.
Aggregate Rating 1519 ± 20, rank #724 of 1656 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Helpfulness | 0.48 | Helpfulness Score | 95.8 |
| Open LLM Leaderboard - MuSR | 48.07 | Score | 94.8 |
| HumanLikeness - Sound-1 | 79.19 | Humanlike Score (%) | 94.7 |
| pfgen-bench - Completion Mode - Score | 0.74 | pfgen Score (mean of three) | 94.2 |
| pfgen-bench - Completion Mode - Truthfulness | 0.91 | Truthfulness Score | 92.7 |
| Open LLM Leaderboard - IFEval | 76.64 | Score | 92.4 |
| LogicKor - Coding | 9.57 | Score (0-10) | 91.6 |
| pfgen-bench - Completion Mode - Fluency | 0.82 | Fluency Score | 91.5 |
| HumanLikeness - Word-1 | 65.8 | Humanlike Score (%) | 89.5 |
| LogicKor - Grammar | 7.78 | Score (0-10) | 87.6 |
| pfgen-bench - QA Mode - Truthfulness | 0.93 | Truthfulness Score | 85.2 |
| LogicKor - Multi-Turn | 8.09 | Score (0-10) | 84 |
Interactive version: theaggregate.ai/model?slug=c4ai-command-r-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.