Model Comparison

Codestral-22B vs GPT-5.6 LunaWhich is better in 2026?

Comparing Codestral-22B and GPT-5.6 Luna across benchmarks, pricing, and capabilities.

Verdict: Codestral-22B vs GPT-5.6 Luna — which is better?

Codestral-22B (by Mistral AI) and GPT-5.6 Luna (by OpenAI) 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 need open weights you can self-host or fine-tune

Choose GPT-5.6 Luna if…

  • you want the most recent training data — it shipped Jul 2026

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and GPT-5.6 Lunadon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only GPT-5.6 Luna specifies input context (1,050,000 tokens). Only GPT-5.6 Luna specifies output context (128,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
OpenAI
GPT-5.6 Luna
Input1,050,000 tokens
Output128,000 tokens
Sat Jul 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

GPT-5.6 Luna supports multimodal inputs, whereas Codestral-22B does not.

GPT-5.6 Luna can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

GPT-5.6 Luna

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while GPT-5.6 Luna uses a proprietary license.

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

Codestral-22B

MNPL-0.1

Open weights

GPT-5.6 Luna

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while GPT-5.6 Luna was released on 2026-07-09.

GPT-5.6 Luna is 26 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.1 years ago

GPT-5.6 Luna

Jul 9, 2026

1 weeks ago

2.1yr newer

Knowledge Cutoff

When training data ends

GPT-5.6 Luna has a documented knowledge cutoff of 2026-02-16, while Codestral-22B's cutoff date is not specified.

We can confirm GPT-5.6 Luna's training data extends to 2026-02-16, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

GPT-5.6 Luna

Feb 2026

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Mistral AI
Has open weights
OpenAI
Larger context window (1,050,000 tokens)
Supports multimodal inputs

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Codestral-22B and GPT-5.6 Luna side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
GPT-5.6 Luna
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
OpenAI
GPT-5.6 Luna

FAQ

Common questions about Codestral-22B vs GPT-5.6 Luna.

Which is better, Codestral-22B or GPT-5.6 Luna?

Codestral-22B (Mistral AI) and GPT-5.6 Luna (OpenAI) 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 GPT-5.6 Luna in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. GPT-5.6 Luna scores Connectors: 99.9%, HealthBench Consensus: 95.1%, GPQA: 92.3%, Search and Function-Calling: 89.7%, Capture-the-Flag Challenges (Internal): 85.2%.

What are the context window sizes for Codestral-22B and GPT-5.6 Luna?

Codestral-22B supports an unknown number of tokens and GPT-5.6 Luna supports 1.1M 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 GPT-5.6 Luna?

Key differences include multimodal support (no vs yes), licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and GPT-5.6 Luna?

Codestral-22B is developed by Mistral AI and GPT-5.6 Luna is developed by OpenAI.

Related comparisons