c4ai-command-r-v01 — benchmark results

CohereForAI Command R v01 open-weight checkpoint. Provider: Cohere. Released 2024-03-11. Access: Open.

Unified ELO 1451 ± 17, rank #992 of 1776 rated models, from 63 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR16.13Score85
Open LLM Leaderboard - IFEval67.48Score79.9
BiGGen-Bench3.68Average Score (1-5)73.5
EuroEval Portuguese NLU - HAREM48.64Named entity recognition Score (%)73.3
EuroEval Dutch NLU - DBRD90.19Sentiment classification Score (%)72.6
BABILong (NIAH)55.3Avg Accuracy (%)72.4
EuroEval Italian NLU - MultiNERD IT69.33Named entity recognition Score (%)70.3
EuroEval Spanish NLU - Sentiment Headlines ES45.06Sentiment classification Score (%)69.7
Open LLM Leaderboard - BBH34.56Score68.7
EuroEval Spanish NLU47.43NLU Average Score (%)66.3
EuroEval Portuguese NLU53.05NLU Average Score (%)66.1
Open PL LLM - Generative57.25Average Generative Score (%)64.7

Interactive version: theaggregate.ai/model?slug=c4ai-command-r-v01 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.