Command A Plus: Specs & Sources

Command A Plus benchmarks

Speed

20 of 100 models

Mercury 2.5576tokens/s

Gemini 3.1 Flash-Lite336tokens/s

Gemini 3.5 Flash-Lite299tokens/s

Nemotron 3.5 Lightning245tokens/s

Claude Haiku 5.5236tokens/s

o3-mini230tokens/s

Ling 3.0 Flash199tokens/s

DeepSeek-V3 0324195tokens/s

GPT-5.4 mini191tokens/s

Gemini 3 Flash Preview191tokens/s

Gemini 3.5 Flash184tokens/s

Gemini 3.6 Flash182tokens/s

Command A Plus177tokens/s

DeepSeek-V4.1-Flash176tokens/s

DeepSeek V4.1 Flash 1017172tokens/s

Qwen 3.7 Max165tokens/s

GPT-5.4 nano153tokens/s

GPT OSS 20B152tokens/s

GPT OSS 120B151tokens/s

Claude Sonnet 5.5151tokens/s

Mercury 2.5

Gemini 3.1 Flash-Lite

Gemini 3.5 Flash-Lite

Nemotron 3.5 Lightning

Gemini 3 Flash Preview

Gemini 3.5 Flash

Gemini 3.6 Flash

Command A Plus

DeepSeek-V4.1-Flash

DeepSeek V4.1 Flash 1017

Output tokens per second, measured by Artificial Analysis

Command A Plus by task area

Points, 100 = reference group average · higher is better

GeneralRank 59 of 6549.6

Knowledgetoo little data43.9

Multimodaltoo little data38.9

AgentsRank 92 of 9838.1

CodingRank 106 of 10935.7

ReasoningRank 68 of 7235.0

HealthRank 71 of 7225.6

Legaltoo little data25.6

Financetoo little data17.2

Light bar: too few results for a rank yet. No tests yet: Mathematics.

Show all 132 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AutomationBench-AA: Overall (Show measurement, test conditions, and source)

Source value: 1.8104537047977383
Score: 1.8104537047977383
Metric: Objectives completed without guardrail violations
Unit: %
Benchmark version: AA private 657-task split of AutomationBench v1.0.6
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 1.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-automationbench-aa:AA private 657-task split of AutomationBench v1.0.6:v5.0:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Reasoning: reasoning enabled
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

AutomationBench-AA: Overall (Show measurement, test conditions, and source)

Source value: 1.8104537047977383
Score: 1.8104537047977383
Metric: Objectives completed without guardrail violations
Unit: %
Benchmark version: AA private 657-task split of AutomationBench v1.0.6
Category: agentic
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-11-07
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 1.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-automationbench-aa:AA private 657-task split of AutomationBench v1.0.6:v5.0.1:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Reasoning: reasoning enabled

Source Artificial Analysis

CritPt v2 (Hard Subset): Overall (Show measurement, test conditions, and source)

Source value: 2.5
Score: 2.5
Metric: pass@1 accuracy
Unit: %
Benchmark version: v2 hard subset
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 2.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2-hard-subset:v2 hard subset:v5.0:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Reasoning: reasoning enabled
Context: This is the 40-question hard subset of CritPt v2, not the full 70-question CritPt v2 run.. This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

CritPt v2 (Hard Subset): Overall (Show measurement, test conditions, and source)

Source value: 2.5
Score: 2.5
Metric: pass@1 accuracy
Unit: %
Benchmark version: v2 hard subset, November 2026 grading
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-11-07
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 2.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-critpt-v2-hard-subset:v2 hard subset, November 2026 grading:v5.0.1:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Reasoning: reasoning enabled
Context: This is the 40-question hard subset of CritPt v2, not the full 70-question CritPt v2 run.

Source Artificial Analysis

CritPt v2: Overall (Show measurement, test conditions, and source)

Source value: 0.28571428571428603
Score: 0.28571428571428603
Metric: pass@1 accuracy
Unit: %
Benchmark version: v2
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: disputed
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled. Score display: 0.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled
Context: This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.

Source Artificial Analysis

FrontierCode: Overall (Show measurement, test conditions, and source)

Source value: 0
Score: 0
Metric: Mean score over three attempts per task
Unit: %
Benchmark version: 2.0
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 0.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-frontiercode-2-0:2.0:v5.0:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Reasoning: reasoning enabled
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

FrontierCode: Overall (Show measurement, test conditions, and source)

Source value: 0
Score: 0
Metric: Mean score over three attempts per task
Unit: %
Benchmark version: 2.0
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-11-07
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 0.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-frontiercode-2-0:2.0:v5.0.1:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Reasoning: reasoning enabled

Source Artificial Analysis

FrontierCode 1.1 Main: Overall (Show measurement, test conditions, and source)

Source value: 1.21166666666667
Score: 1.21166666666667
Metric: Mean score over three attempts per task
Unit: %
Benchmark version: 1.1 Main
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled. Score display: 1.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-frontiercode:1.1 Main:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled
Context: FrontierCode 1.1 Main is a private 100-task subset of 150 tasks. These are AA mean rubric scores, not a binary pass rate.. This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

FrontierCode 1.1 Main: Overall (Show measurement, test conditions, and source)

Source value: 1.21166666666667
Score: 1.21166666666667
Metric: Mean score over three attempts per task
Unit: %
Benchmark version: 1.1 Main
Category: coding
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-11-07
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled. Score display: 1.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-frontiercode:1.1 Main:standalone:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The primary 100-task FrontierCode 1.1 set is run three times per task, with equal task weights. Failing any blocking check or being flagged by the trajectory scanner scores zero; runs passing every blocking check score 70 to 100 percent.. Harness: Artificial Analysis Stirrup. Agent: Stirrup coding agent. Tool policy: 250-turn cap; repository worktree graded as left by the agent. Attempts: Mean score, 3 attempts per task. Reasoning: reasoning enabled
Context: FrontierCode 1.1 Main is a private 100-task subset of 150 tasks. These are AA mean rubric scores, not a binary pass rate.

Source Artificial Analysis

GDP.pdf: Overall (Show measurement, test conditions, and source)

Source value: 1
Score: 1
Metric: All-pass rate
Unit: %
Benchmark version: unspecified
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 1.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-gdp-pdf:unspecified:v5.0:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Reasoning: reasoning enabled
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

GDP.pdf: Overall (Show measurement, test conditions, and source)

Source value: 1
Score: 1
Metric: All-pass rate
Unit: %
Benchmark version: unspecified
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-11-07
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 1.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-gdp-pdf:unspecified:v5.0.1:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count.. Reasoning: reasoning enabled

Source Artificial Analysis

HLE-Diamond: Overall (Show measurement, test conditions, and source)

Source value: 5.1
Score: 5.1
Metric: pass@1 accuracy
Unit: %
Benchmark version: Diamond
Category: general
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: superseded
Retrieved at: 2026-11-02
Methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Source model ID: artificial-analysis/2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e/command-a-plus/command-a-plus. Source model name: Command A Plus. Provider reported by source: Cohere. Model snapshot: Command A+. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Score display: 5.1%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-hle-diamond:Diamond:v5.0:reasoning:effort=unspecified:suffix=unspecified
Comparison methodology: Exact AA configuration: Command A+ (release command-a-plus, row command-a-plus, UUID 2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap.. Reasoning: reasoning enabled
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Artificial Analysis

Page 1 of 11

See for yourself: one prompt, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Command A Plus

Earlier tests

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 1, 2026 · 21 s · $0.0072

Test details

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: cohere/command-a-plus
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 4,817 tokens
Cost of the attempt: $0.0072
Response time: 21 s
API model reported in response: cohere/command-a-plus
Pinned endpoint: Cohere | cohere/command-a-plus-05-2026
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Task origin: Simon Willison

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

GPT-6 Astra83

Claude Haiku 5.577

GPT-6 Sol73

GPT-573

DeepSeek V4.1 Flash 101769

Kimi K367

MiniCPM-V 4.7 35B-A3B63

Command A Plus33

DeepSeek V4.1 Flash 1017

MiniCPM-V 4.7 35B-A3B

GPT-6.1 Sol

Claude Opus 5

Qwen 3.8 Flash

Command A Plus

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 7, 2026

Command A PlusAmazon Nova Pro 33Aya Expanse 32B 33AREX-2 33Nex-N2-mini 33

Method changes in the timeline, a jump at these points is no market event:

1November 1, 2026: Value only with search or usage data, 30-day attention

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

Similar models

More models of the same kind as Command A Plus, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Parameters: 218 billion; Source: Parameters
Active parameters: 25 billion; Source: Active parameters
Knowledge cutoff: April 2025; Source: Knowledge cutoff

Input and output

Context window: 128,000 tokens; Source: Context window
Maximum output: 64,000 tokens; Source: Maximum output
Inputs: Text, Image; Source: Inputs
Outputs: Text; Source: Outputs
Reasoning: Yes; Source: Reasoning
Tool calling: Yes; Source: Tool calling

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Weights: Open weights; Source: Weights
Access: API; Source: Access
License: CC BY-NC-4.0; Source: License

Prices

Not included in any subscription in Germany.

All plans in the AI subscription comparison

Frequently asked questions about Command A Plus

How good is Command A Plus in benchmarks?

Not ranked in the overall index yet; the provisional value is 32.9 points. The value is provisional because there are not yet enough results for a fixed place.

Overall index (Gradually Meta-Score v4) from 17 benchmark results · data through Nov 7, 2026

What is the Overall index (Gradually Meta-Score v4)?

A point value that combines many independent benchmarks into one number. 100 points is the average of a fixed reference group, higher is better. Command A Plus has a provisional 32.9 points, not yet ranked.

Own analysis by gradually.ai, method benchmark-meta-score-v4 · for Command A Plus from 17 test series

Which data: Only current, reviewed results from independent evaluators such as Artificial Analysis, Vals AI, LMArena, LiveBench and Epoch AI. Vendor claims and historical or disputed values do not count.
One value per test: For each source and test series the latest retrieval with one fixed setup counts. When a source tests several reasoning levels, the highest documented one applies. A series needs at least 5 models.
Making tests comparable: Percentages are converted so that gaps near 0 and near 100 % count fairly, then every series is put on the same scale. A hard test therefore does not weigh more than an easy one.
Shared strength: A statistical model estimates, from all series at once, one shared capability per model and, per area, how far a model deviates from it. Missing tests are never counted as zero.
Weighting: Core areas (Coding, Reasoning, Mathematics, Knowledge, Agents, General and Multimodal) count 75 % together, the domain areas Finance, Legal and Health 25 %.
The point scale: The value is measured against a fixed reference group of 29 models, much like an IQ score: 100 points is its average and 15 points one standard deviation of the group. The scale is open at both ends and is not a percentage. A model 15 points ahead does better in roughly three of four benchmark comparisons. New models do not shift older values.
Place by score: The place follows the order of the scores among all models with a place, such as "rank 14 of 95". A second calculation checks whether a lead is reliable by recomputing the score 200 times with randomly redrawn test families. If a model is not almost always ahead there, the two models count as level.
Minimum evidence: A value needs at least 8 test series from 2 sources and 3 areas, a place only with enough precision. Missing core areas are flagged as "estimated".
What it is not: Not a test run by gradually.ai and no verdict on every single task. For a specific task the area values and the individual benchmarks matter more.

What is the knowledge cutoff of Command A Plus?

April 2025, according to Cohere. That is 13 months before release.

Stated by Cohere

AprJulOctJanAprKnowledge cutoffApril 2025ReleasedMay 20, 2026

How large is the context window of Command A Plus?

128,000 tokens. That is how much text Command A Plus reads at once, about 190 A4 pages.

Page count as a rule of thumb from Artificial Analysis

Context windowTokens the model reads at once · higher is better

GLM-5.1200K

DeepSeek-V3 0324164K

GLM-4.5131K

GPT OSS 120B131K

Command A PlusRank 98 of 102128K

DeepSeek-V3.2128K

DeepSeek-R1128K

How fast is Command A Plus?

177 tokens per second. That is faster than a typical model at 87.

Measured by Artificial Analysis on Nov 6, 2026. AA 3.0.0, including time to first token, averaged across available workloads and five days.

SpeedTokens per second · higher is better

Gemini 3 Flash Preview191

Gemini 3.5 Flash184

Gemini 3.6 Flash182

Command A PlusRank 13 of 100177

DeepSeek-V4.1-Flash176

DeepSeek V4.1 Flash 1017172

Qwen 3.7 Max165

Can I run Command A Plus locally?

Yes, the weights are open. With 218B parameters it needs a lot of memory, more a server than a laptop.

Stated by Cohere

Open weights: yes
License: CC BY-NC-4.0
Parameters: 218B
active per token: 25B

Sources and data date

Show all 42 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

Evaluator	Test series	Composite indices	Recorded active measurements
Artificial Analysis	20	0	34
Vals AI	4	0	19

Without vendor claims and historical or disputed results; those stay labelled in the single values.

Type	Evidence and data date
Speed	Cohere, Reasoning enabled; effort unspecified. AA 3.0.0, including time to first token, averaged across available workloads and five days. Retrieved November 6, 2026. Source: Artificial Analysis · Speed (Artificial Analysis)Speed measurement methodology
Input	Documented modalities. Retrieved October 27, 2026. Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026)
Output	Documented modalities. Retrieved October 27, 2026. Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026)
Research status	Research date October 15, 2026. 11 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published	evaluation-details Note The post gives methodology notes but not full task snapshots, exact run counts or complete model-serving parameters for these rows.
Not published	AA per-profile sample counts Original wording Evaluator methodology task totals and repeats are published, but the exact Command A+ completed/scored denominator for each model-page field is not. No sampleCount has been populated.
Not published	AA model-page benchmark prompts and effort Original wording The profile is marked reasoning-enabled with reasoningTokens=2000, but the source does not bind those fields to each individual evaluation's executed prompt or effort.
Unresolved	Artificial Analysis Intelligence Index discrepancy Original wording Cohere's official launch page reports an unversioned index score of 37, while the current exact AA profile reports v4.3.2 value 13.1335002685349. Versions/execution are not comparable from the available record; current AA row is marked disputed.
Unresolved	CritPt status Original wording The exact profile exposes a numeric CritPt field, but AA's CritPt evaluator page says Under review with an expert audit underway; excluded rather than treated as a confirmed measurement.
Additional source	Artificial Analysis (retrieved October 29, 2026; November 2, 2026; November 7, 2026)1 2
Additional source	Artificial Analysis (retrieved November 2, 2026; November 7, 2026)1 2 3 4 5 6 7 8
Additional source	Artificial Analysis (retrieved October 17, 2026; November 2, 2026)
Additional source	Artificial Analysis (retrieved November 7, 2026)1 2 3
Additional source	Artificial Analysis (retrieved November 2, 2026)
Additional source	Artificial Analysis (retrieved October 17, 2026; November 2, 2026; November 7, 2026)
Additional source	Vals AI (retrieved November 7, 2026)1 2 3 4
Additional source	Vals AI (retrieved October 16, 2026; October 30, 2026; October 31, 2026)
Additional source	Cohere Command A+ release evaluation notes (retrieved October 15, 2026; October 17, 2026)
Additional source	Artificial Analysis, Command A+ model profile (retrieved October 17, 2026)
Additional source	ToneBench, Cohere Command A+ (05-2026) profile (retrieved October 17, 2026; October 20, 2026; October 28, 2026; October 30, 2026)
Additional source	Red Hat AI, Command A+ 05-2026 FP8 Hugging Face model card, Evaluation > Accuracy table (BF16 comparator column) (retrieved October 18, 2026)
Additional source	Model metadata (retrieved October 15, 2026; October 17, 2026)
Additional source	Model metadata (retrieved October 17, 2026)1 2 3
Additional source	Model metadata (retrieved October 18, 2026)
Additional source	Cohere current model overview · Editorial description reviewed October 2, 2026
Additional source	Cohere Command A Plus documentation · Editorial description reviewed October 2, 2026
Additional source	Cohere Command A Plus model card · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0