GeekRadar / The comparison desk

COMPARE.

AI models

cohere

Command R

AI model Released Aug 30, 2024

Context window: 128,000 tokens
Maximum output: 4,000 tokens
Open weights: Yes

Capability & preference

Human preference · Arena

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

Command R 1187.3 command-r-08-2024 · 95% interval 1180.8–1193.8 · 10,140 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

1,182.20 rating

Confidence interval: 1,162.22 – 1,202.18

834 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Command R

1,169.25 rating

Confidence interval: 1,155.90 – 1,182.60

1783 votes

Oct 15, 2026

Category: coding
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Command R

1,169.76 rating

Confidence interval: 1,154.43 – 1,185.09

1421 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Command R

1,197.70 rating

Confidence interval: 1,189.38 – 1,206.01

5416 votes

Oct 15, 2026

Category: english
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Command R

1,056.23 rating

Confidence interval: 1,045.63 – 1,066.82

6414 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Command R

1,137.46 rating

Confidence interval: 1,115.54 – 1,159.38

604 votes

Oct 15, 2026

Category: expert
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Command R

1,176.20 rating

Confidence interval: 1,143.21 – 1,209.19

275 votes

Oct 15, 2026

Category: german
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Command R

1,164.07 rating

Confidence interval: 1,153.78 – 1,174.35

2976 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Command R

1,170.63 rating

Confidence interval: 1,157.76 – 1,183.51

1822 votes

Oct 15, 2026

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 · 2026-10-15 · rating

Command R

1,157.10 rating

Confidence interval: 1,139.78 – 1,174.42

1152 votes

Oct 15, 2026

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 · 2026-10-15 · rating

Command R

1,161.96 rating

Confidence interval: 1,147.84 – 1,176.09

1593 votes

Oct 15, 2026

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 · 2026-10-15 · rating

Command R

1,229.41 rating

Confidence interval: 1,205.34 – 1,253.47

569 votes

Oct 15, 2026

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 · 2026-10-15 · rating

Command R

1,218.23 rating

Confidence interval: 1,203.85 – 1,232.60

1620 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Command R

1,165.49 rating

Confidence interval: 1,150.98 – 1,180.01

1361 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Command R

1,208.27 rating

Confidence interval: 1,182.68 – 1,233.87

500 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Command R

1,173.57 rating

Confidence interval: 1,162.64 – 1,184.51

2845 votes

Oct 15, 2026

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 · 2026-10-15 · rating

Command R

1,193.06 rating

Confidence interval: 1,181.49 – 1,204.63

2597 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Command R

1,166.92 rating

Confidence interval: 1,157.80 – 1,176.04

4153 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Command R

1,143.12 rating

Confidence interval: 1,109.76 – 1,176.48

254 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Command R

1,162.51 rating

Confidence interval: 1,111.59 – 1,213.43

152 votes

Oct 15, 2026

Category: korean
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Command R

1,197.39 rating

Confidence interval: 1,182.63 – 1,212.14

1421 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Command R

1,154.79 rating

Confidence interval: 1,141.21 – 1,168.37

1601 votes

Oct 15, 2026

Category: math
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Command R

1,163.02 rating

Confidence interval: 1,149.34 – 1,176.70

1851 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Command R

1,174.26 rating

Confidence interval: 1,165.38 – 1,183.14

4724 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Command R

1,187.32 rating

Confidence interval: 1,180.80 – 1,193.84

10140 votes

Oct 15, 2026

Category: overall
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Command R

1,173.85 rating

Confidence interval: 1,158.24 – 1,189.46

1350 votes

Oct 15, 2026

Category: russian
Evaluated configuration: command-r-08-2024
Evaluation type: human preference

Run it locally

Inference · memory estimate

Command R

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Command R

Provider offer

Command R / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
CohereCommand RStandard	Input	USD	0.15 / 1M tokens
CohereCommand RStandard	Output	USD	0.6 / 1M tokens

Capabilities

Context window: 128,000 tokens
Maximum output: 4,000 tokens
Reasoning: No
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2024-06-01
Model license: CC-BY-NC-4.0

Input modalities

text

Output modalities

text