The AI arena is free today

Open Superagent

Codestral-22B vs GPT-6 Rosalind

Comparing Codestral-22B and GPT-6 Rosalind across benchmarks, pricing, and capabilities.

Mistral AI · OpenAI · Updated for 2026

Which is better?

Codestral-22B and GPT-6 Rosalind trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Codestral-22B

  • you need open weights you can self-host or fine-tune

Choose GPT-6 Rosalind

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
GPT-6 Rosalind
OpenAI
Benchmark wins
—
—
Input price
— / M
$15.00 / M
Output price
— / M
$75.00 / M
Context window
—
—

Individual benchmarks

7 reported for Codestral-22B · 0 for GPT-6 Rosalind

No common benchmarks found

Codestral-22B and GPT-6 Rosalinddon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Input capabilities

Documented input modalities across available providers

GPT-6 Rosalind supports multimodal inputs, whereas Codestral-22B does not.

GPT-6 Rosalind can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

GPT-6 Rosalind

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while GPT-6 Rosalind 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-6 Rosalind

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while GPT-6 Rosalind was released on 2026-10-30.

GPT-6 Rosalind is 29 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.4 years ago

GPT-6 Rosalind

Oct 30, 2026

1 days ago

2.4yr 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?

Judge for yourself.

Run your own prompts against Codestral-22B and GPT-6 Rosalind side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
GPT-6 Rosalind
Open in Playground

FAQ

Common questions about Codestral-22B vs GPT-6 Rosalind.

Which is better, Codestral-22B or GPT-6 Rosalind?

Codestral-22B (Mistral AI) and GPT-6 Rosalind (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-6 Rosalind in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%.

What are the main differences between Codestral-22B and GPT-6 Rosalind?

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-6 Rosalind?

Codestral-22B is developed by Mistral AI and GPT-6 Rosalind is developed by OpenAI.

Related comparisons