Cohere: Command A

● Excellent

by Cohere Open Weight Intelligent Agentic Rank #61 of 80

8.0
/ 10

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

Choose a model to compare against Cohere: Command A

Specifications

Specifications for Cohere: Command A
AttributeValue
Lab Cohere
Tags Open Weight Intelligent Agentic
Overall Score 8.0/10
Release Date 2025-03
Context Window 256,000 tokens
Input Price / 1M $2.50
Output Price / 1M $10.00
Input Modalities Text
Output Modalities Text

Strengths

  • Open-weights 111B model with 256k context window
  • Strong multilingual and agentic performance
  • Competitive coding and RAG capabilities
  • Efficient for enterprise deployment

Weaknesses

  • Less competitive on pure reasoning benchmarks
  • Smaller ecosystem than Llama/Qwen open models
  • Limited community fine-tunes and tooling

Best For

  • Enterprise RAG and search applications
  • Multilingual tasks
  • Long-context document processing
  • Agentic workflows

Sources & Further Reading

Related Models

Scores are aggregated from public benchmarks (MMLU, HumanEval, MATH, GSM8K, LMSYS) and normalized to a 1–10 scale. Methodology →