Command-R+ (08-2024) — benchmark results

August 2024 Command R+ variant, tracked separately from the Command R August 2024 checkpoint. Provider: Cohere. Released 2024-08-21. Access: Open.

Unified ELO 1468 ± 20, rank #913 of 1776 rated models, from 57 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open CoT - LSAT Logical Reasoning23.73CoT Gain (%)99.2
Open LLM Leaderboard - MuSR19.84Score94.6
Open LLM Leaderboard - IFEval75.4Score90.9
Open CoT - LogiQA 214.76CoT Gain (%)90.8
Open LLM Leaderboard - GPQA13.42Score87.9
Open CoT Leaderboard12.61Average CoT Gain (%)84.7
Open LLM Leaderboard - BBH42.84Score82
Open LLM Leaderboard - MMLU-Pro38.01Score82
LiveBench Zebra Puzzle38Score79.2
Open CoT - LSAT Reading Comprehension18.22CoT Gain (%)77.5
LiveBench Summarize65.87Score76.4
LiveBench Typos44Score72.9

Interactive version: theaggregate.ai/model?slug=command-r-plus-08-2024 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.