The AI arena is free today

Open Superagent

Codestral-22B vs Grok 4.6

Comparing Codestral-22B and Grok 4.6 across benchmarks, pricing, and capabilities.

Mistral AI · xAI · Updated for 2026

Which is better?

Codestral-22B and Grok 4.6 trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Codestral-22B

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

Choose Grok 4.6

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

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Grok 4.6
xAI
Benchmark wins
—
—
Input price
— / M
$2.00 / M
Output price
— / M
$6.00 / M
Context window
—
500,000
Released
May 2024
Aug 2026
License
MNPL-0.1
Proprietary

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Grok 4.6don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Arena Performance

Playground indexes and blind preference scores

Context Window

Maximum input and output token capacity

Only Grok 4.6 specifies input context (500,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
xAI
Grok 4.6
Input500,000 tokens
Output- tokens
Tue Aug 25 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Grok 4.6 supports multimodal inputs, whereas Codestral-22B does not.

Grok 4.6 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Grok 4.6

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Grok 4.6 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

Grok 4.6

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Grok 4.6 was released on 2026-08-12.

Grok 4.6 is 27 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.2 years ago

Grok 4.6

Aug 12, 2026

1 weeks ago

2.2yr newer

Knowledge Cutoff

When training data ends

Grok 4.6 has a documented knowledge cutoff of 2026-02-01, while Codestral-22B's cutoff date is not specified.

We can confirm Grok 4.6's training data extends to 2026-02-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Grok 4.6

Feb 2026

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Codestral-22B and Grok 4.6 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Grok 4.6
Open in Playground

FAQ

Common questions about Codestral-22B vs Grok 4.6.

Which is better, Codestral-22B or Grok 4.6?

Codestral-22B (Mistral AI) and Grok 4.6 (xAI) 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 Grok 4.6 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Grok 4.6 scores CursorBench v3.2: 69.9%, DeepSWE 1.1: 65.9%, FrontierCode: 61.3%, AA-Index: 61.0%, GDPval-AA: 58.4%.

What are the context window sizes for Codestral-22B and Grok 4.6?

Codestral-22B supports an unknown number of tokens and Grok 4.6 supports 500K 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 Grok 4.6?

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 Grok 4.6?

Codestral-22B is developed by Mistral AI and Grok 4.6 is developed by xAI.

Related comparisons