GeekRadar / The comparison desk
COMPARE.
AI models
cohere

Command R (08-2024)

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Command R (08-2024) 1187.3 Command R (08-2024) · 95% interval 1180.8–1193.9 · 10,140 votes · 2026-10-28

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-28 · rating

Command R (08-2024)

1,182.15 rating

Confidence interval: 1,162.17 – 1,202.12

834 votes

Category
chinese
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Command R (08-2024)

1,169.15 rating

Confidence interval: 1,155.80 – 1,182.50

1783 votes

Category
coding
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Command R (08-2024)

1,169.60 rating

Confidence interval: 1,154.28 – 1,184.93

1421 votes

Category
creative_writing
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,197.75 rating

Confidence interval: 1,189.43 – 1,206.06

5416 votes

Category
english
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Command R (08-2024)

1,056.22 rating

Confidence interval: 1,045.62 – 1,066.81

6414 votes

Category
exclude_ties
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Command R (08-2024)

1,137.42 rating

Confidence interval: 1,115.51 – 1,159.33

604 votes

Category
expert
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,176.20 rating

Confidence interval: 1,143.19 – 1,209.21

275 votes

Category
german
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Command R (08-2024)

1,164.08 rating

Confidence interval: 1,153.80 – 1,174.36

2976 votes

Category
hard_prompts
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,170.75 rating

Confidence interval: 1,157.87 – 1,183.62

1822 votes

Category
hard_prompts_english
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Command R (08-2024)

1,157.06 rating

Confidence interval: 1,139.74 – 1,174.38

1152 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Command R (08-2024)

1,161.90 rating

Confidence interval: 1,147.78 – 1,176.03

1593 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Command R (08-2024)

1,229.66 rating

Confidence interval: 1,205.60 – 1,253.72

569 votes

Category
industry_legal_and_government
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Command R (08-2024)

1,218.25 rating

Confidence interval: 1,203.87 – 1,232.62

1620 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,165.50 rating

Confidence interval: 1,150.98 – 1,180.01

1361 votes

Category
industry_mathematical
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Command R (08-2024)

1,208.22 rating

Confidence interval: 1,182.63 – 1,233.80

500 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Command R (08-2024)

1,173.49 rating

Confidence interval: 1,162.55 – 1,184.43

2845 votes

Category
industry_software_and_it_services
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Command R (08-2024)

1,193.00 rating

Confidence interval: 1,181.43 – 1,204.57

2597 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Command R (08-2024)

1,166.91 rating

Confidence interval: 1,157.79 – 1,176.03

4153 votes

Category
instruction_following
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Command R (08-2024)

1,143.29 rating

Confidence interval: 1,109.89 – 1,176.69

254 votes

Category
japanese
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,162.47 rating

Confidence interval: 1,111.54 – 1,213.40

152 votes

Category
korean
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,197.34 rating

Confidence interval: 1,182.59 – 1,212.09

1421 votes

Category
longer_query
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,154.83 rating

Confidence interval: 1,141.25 – 1,168.41

1601 votes

Category
math
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,163.02 rating

Confidence interval: 1,149.34 – 1,176.70

1851 votes

Category
multi_turn
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,174.17 rating

Confidence interval: 1,165.28 – 1,183.05

4724 votes

Category
non_english
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,187.34 rating

Confidence interval: 1,180.82 – 1,193.85

10140 votes

Category
overall
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Command R (08-2024)

1,173.70 rating

Confidence interval: 1,158.09 – 1,189.31

1350 votes

Category
russian
Evaluated configuration
Command R (08-2024)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Command R (08-2024)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
CC-BY-NC-4.0