GeekRadar / The comparison desk
COMPARE.
AI models
cohere

command-r-plus

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-plus 1203.8 command-r-plus · 95% interval 1199.5–1208.1 · 77,554 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-plus

1,190.96 rating

Confidence interval: 1,181.16 – 1,200.76

10474 votes

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

command-r-plus

1,171.62 rating

Confidence interval: 1,163.97 – 1,179.28

13937 votes

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

command-r-plus

1,200.81 rating

Confidence interval: 1,192.26 – 1,209.37

11012 votes

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

command-r-plus

1,213.09 rating

Confidence interval: 1,207.82 – 1,218.36

42376 votes

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

command-r-plus

1,090.73 rating

Confidence interval: 1,084.46 – 1,097.00

51313 votes

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

command-r-plus

1,153.22 rating

Confidence interval: 1,140.87 – 1,165.57

4031 votes

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

command-r-plus

1,208.57 rating

Confidence interval: 1,185.64 – 1,231.51

1226 votes

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

command-r-plus

1,195.47 rating

Confidence interval: 1,180.18 – 1,210.75

2864 votes

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

command-r-plus

1,166.36 rating

Confidence interval: 1,160.02 – 1,172.69

22394 votes

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

command-r-plus

1,171.14 rating

Confidence interval: 1,163.55 – 1,178.73

13980 votes

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

command-r-plus

1,190.46 rating

Confidence interval: 1,181.06 – 1,199.86

8504 votes

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

command-r-plus

1,189.57 rating

Confidence interval: 1,181.32 – 1,197.82

11264 votes

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

command-r-plus

1,244.71 rating

Confidence interval: 1,232.42 – 1,257.00

4403 votes

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

command-r-plus

1,216.19 rating

Confidence interval: 1,207.89 – 1,224.48

13227 votes

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

command-r-plus

1,165.14 rating

Confidence interval: 1,156.19 – 1,174.09

8796 votes

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

command-r-plus

1,203.27 rating

Confidence interval: 1,190.51 – 1,216.03

4198 votes

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

command-r-plus

1,185.77 rating

Confidence interval: 1,179.20 – 1,192.34

22666 votes

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

command-r-plus

1,218.70 rating

Confidence interval: 1,211.61 – 1,225.79

19567 votes

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

command-r-plus

1,179.52 rating

Confidence interval: 1,173.49 – 1,185.56

28069 votes

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

command-r-plus

1,154.61 rating

Confidence interval: 1,135.35 – 1,173.86

1487 votes

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

command-r-plus

1,137.88 rating

Confidence interval: 1,117.75 – 1,158.02

1919 votes

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

command-r-plus

1,201.33 rating

Confidence interval: 1,192.41 – 1,210.25

9149 votes

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

command-r-plus

1,164.36 rating

Confidence interval: 1,155.89 – 1,172.82

9769 votes

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

command-r-plus

1,192.15 rating

Confidence interval: 1,183.72 – 1,200.58

12101 votes

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

command-r-plus

1,189.46 rating

Confidence interval: 1,183.83 – 1,195.10

35178 votes

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

command-r-plus

1,203.79 rating

Confidence interval: 1,199.51 – 1,208.08

77554 votes

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

command-r-plus

1,238.43 rating

Confidence interval: 1,184.11 – 1,292.75

216 votes

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

command-r-plus

1,205.87 rating

Confidence interval: 1,196.49 – 1,215.25

7778 votes

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

command-r-plus

1,189.01 rating

Confidence interval: 1,166.19 – 1,211.83

1174 votes

Category
spanish
Evaluated configuration
command-r-plus
Evaluation type
human preference

Run it locally

Inference · memory estimate

command-r-plus

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
CC-BY-NC-4.0