GeekRadar / The comparison desk

COMPARE.

AI models

cohere

Command A

AI model Released Mar 13, 2025

Context window: 256,000 tokens
Maximum output: 8,000 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 A 1330.9 command-a-03-2025 · 95% interval 1327.5–1334.4 · 55,766 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 A

1,327.37 rating

Confidence interval: 1,317.46 – 1,337.28

3823 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,330.01 rating

Confidence interval: 1,323.84 – 1,336.19

10234 votes

Oct 15, 2026

Category: coding
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,319.18 rating

Confidence interval: 1,312.05 – 1,326.32

7602 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,343.57 rating

Confidence interval: 1,339.11 – 1,348.02

26256 votes

Oct 15, 2026

Category: english
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,281.19 rating

Confidence interval: 1,276.28 – 1,286.10

38471 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,295.62 rating

Confidence interval: 1,284.50 – 1,306.74

2885 votes

Oct 15, 2026

Category: expert
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,351.07 rating

Confidence interval: 1,329.03 – 1,373.11

776 votes

Oct 15, 2026

Category: french
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,341.66 rating

Confidence interval: 1,325.43 – 1,357.90

1371 votes

Oct 15, 2026

Category: german
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,326.36 rating

Confidence interval: 1,321.72 – 1,330.99

23760 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,335.02 rating

Confidence interval: 1,328.99 – 1,341.04

11259 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,314.68 rating

Confidence interval: 1,307.89 – 1,321.47

8787 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,306.51 rating

Confidence interval: 1,300.29 – 1,312.74

10058 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,347.63 rating

Confidence interval: 1,337.33 – 1,357.93

3434 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,339.12 rating

Confidence interval: 1,332.58 – 1,345.66

9391 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,312.11 rating

Confidence interval: 1,302.50 – 1,321.72

3654 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,334.66 rating

Confidence interval: 1,323.65 – 1,345.68

3059 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,336.44 rating

Confidence interval: 1,331.37 – 1,341.51

17971 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,327.62 rating

Confidence interval: 1,321.89 – 1,333.35

12801 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,308.65 rating

Confidence interval: 1,303.37 – 1,313.92

15575 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,285.30 rating

Confidence interval: 1,267.45 – 1,303.14

1236 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,285.15 rating

Confidence interval: 1,266.87 – 1,303.42

1116 votes

Oct 15, 2026

Category: korean
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,334.12 rating

Confidence interval: 1,328.02 – 1,340.22

10709 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,300.26 rating

Confidence interval: 1,291.03 – 1,309.49

3994 votes

Oct 15, 2026

Category: math
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,338.50 rating

Confidence interval: 1,331.89 – 1,345.10

9289 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,313.07 rating

Confidence interval: 1,308.74 – 1,317.40

29460 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,330.94 rating

Confidence interval: 1,327.49 – 1,334.39

55766 votes

Oct 15, 2026

Category: overall
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,324.27 rating

Confidence interval: 1,312.96 – 1,335.58

3071 votes

Oct 15, 2026

Category: polish
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,314.09 rating

Confidence interval: 1,305.41 – 1,322.76

4470 votes

Oct 15, 2026

Category: russian
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

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

Command A

1,347.34 rating

Confidence interval: 1,329.84 – 1,364.84

1179 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: command-a-03-2025
Evaluation type: human preference

Run it locally

Inference · memory estimate

Command A

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 A

Provider offer

Capabilities

Context window: 256,000 tokens
Maximum output: 8,000 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