Model Comparison

Codestral-22B vs Command R+Which is better in 2026?

Comparing Codestral-22B and Command R+ across benchmarks, pricing, and capabilities.

Verdict: Codestral-22B vs Command R+ — which is better?

Codestral-22B (by Mistral AI) and Command R+ (by Cohere) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Choose Codestral-22B if…

  • you are already invested in the Mistral AI ecosystem

Choose Command R+ if…

  • you want the most recent training data — it shipped Aug 2024

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Command R+don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Human preference votes

Model Size

Parameter count comparison

81.8B diff

Command R+ has 81.8B more parameters than Codestral-22B, making it 368.5% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Cohere
Command R+
104.0Bparameters
22.2B
Codestral-22B
104.0B
Command R+

Context Window

Maximum input and output token capacity

Only Command R+ specifies input context (128,000 tokens). Only Command R+ specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Cohere
Command R+
Input128,000 tokens
Output128,000 tokens
Tue Aug 04 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Command R+ uses CC BY-NC.

License differences may affect how you can use these models in commercial or open-source projects.

Codestral-22B

MNPL-0.1

Open weights

Command R+

CC BY-NC

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Command R+ was released on 2024-08-30.

Command R+ is 3 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

Command R+

Aug 30, 2024

1.9 years ago

3mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Mistral AI

No standout differentiators in the data we have for this pair.

Cohere
Larger context window (128,000 tokens)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Codestral-22B and Command R+ side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Command R+
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
Cohere
Command R+

FAQ

Common questions about Codestral-22B vs Command R+.

Which is better, Codestral-22B or Command R+?

Codestral-22B (Mistral AI) and Command R+ (Cohere) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

How does Codestral-22B compare to Command R+ in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Command R+ scores HellaSwag: 88.6%, Winogrande: 85.4%, MMLU: 75.7%, ARC-C: 71.0%, GSM8k: 70.7%.

What are the context window sizes for Codestral-22B and Command R+?

Codestral-22B supports an unknown number of tokens and Command R+ supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Codestral-22B and Command R+?

Key differences include licensing (MNPL-0.1 vs CC BY-NC). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Command R+?

Codestral-22B is developed by Mistral AI and Command R+ is developed by Cohere.

Related comparisons