GeekRadar / The comparison desk
COMPARE.
AI models
cohere

command-r

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 1163.1 command-r · 95% interval 1158.4–1167.8 · 54,036 votes · 2026-10-15

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 · 2026-10-15 · rating

command-r

1,146.42 rating

Confidence interval: 1,135.66 – 1,157.19

8202 votes

Category
chinese
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

command-r

1,127.50 rating

Confidence interval: 1,118.87 – 1,136.12

9645 votes

Category
coding
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

command-r

1,154.15 rating

Confidence interval: 1,144.46 – 1,163.84

7836 votes

Category
creative_writing
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

command-r

1,174.17 rating

Confidence interval: 1,168.27 – 1,180.07

29623 votes

Category
english
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

command-r

1,027.54 rating

Confidence interval: 1,020.45 – 1,034.63

35666 votes

Category
exclude_ties
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

command-r

1,107.38 rating

Confidence interval: 1,093.62 – 1,121.15

2830 votes

Category
expert
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

command-r

1,162.43 rating

Confidence interval: 1,137.03 – 1,187.83

843 votes

Category
french
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

command-r

1,127.62 rating

Confidence interval: 1,108.98 – 1,146.26

1361 votes

Category
german
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

command-r

1,114.56 rating

Confidence interval: 1,107.40 – 1,121.72

15124 votes

Category
hard_prompts
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

command-r

1,122.42 rating

Confidence interval: 1,113.80 – 1,131.03

9264 votes

Category
hard_prompts_english
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

command-r

1,141.25 rating

Confidence interval: 1,130.78 – 1,151.72

5984 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

command-r

1,142.31 rating

Confidence interval: 1,133.12 – 1,151.51

7973 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

command-r

1,206.46 rating

Confidence interval: 1,192.77 – 1,220.14

3073 votes

Category
industry_legal_and_government
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

command-r

1,170.54 rating

Confidence interval: 1,161.31 – 1,179.78

9216 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

command-r

1,124.80 rating

Confidence interval: 1,114.68 – 1,134.92

5906 votes

Category
industry_mathematical
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

command-r

1,152.24 rating

Confidence interval: 1,138.15 – 1,166.32

2900 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

command-r

1,142.58 rating

Confidence interval: 1,135.18 – 1,149.98

15749 votes

Category
industry_software_and_it_services
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

command-r

1,161.67 rating

Confidence interval: 1,153.88 – 1,169.47

13537 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

command-r

1,124.51 rating

Confidence interval: 1,117.80 – 1,131.23

19085 votes

Category
instruction_following
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

command-r

1,093.86 rating

Confidence interval: 1,071.12 – 1,116.60

856 votes

Category
japanese
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

command-r

1,091.69 rating

Confidence interval: 1,069.75 – 1,113.63

1154 votes

Category
korean
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

command-r

1,157.32 rating

Confidence interval: 1,147.41 – 1,167.23

6160 votes

Category
longer_query
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

command-r

1,119.95 rating

Confidence interval: 1,110.48 – 1,129.42

6682 votes

Category
math
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

command-r

1,147.47 rating

Confidence interval: 1,138.04 – 1,156.89

8273 votes

Category
multi_turn
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

command-r

1,143.47 rating

Confidence interval: 1,137.15 – 1,149.79

24413 votes

Category
non_english
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

command-r

1,163.10 rating

Confidence interval: 1,158.37 – 1,167.83

54036 votes

Category
overall
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

command-r

1,207.47 rating

Confidence interval: 1,146.46 – 1,268.49

135 votes

Category
polish
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

command-r

1,157.60 rating

Confidence interval: 1,147.13 – 1,168.08

5283 votes

Category
russian
Evaluated configuration
command-r
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

command-r

1,150.67 rating

Confidence interval: 1,123.90 – 1,177.44

698 votes

Category
spanish
Evaluated configuration
command-r
Evaluation type
human preference

Run it locally

Inference · memory estimate

command-r

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
CC-BY-NC-4.0