Model Comparison

Codestral-22B vs Grok-2Which is better in 2026?

Grok-2 significantly outperforms across most benchmarks.

Verdict: Codestral-22B vs Grok-2 — which is better?

Codestral-22B (by Mistral AI) and Grok-2 (by xAI) 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.

Codestral-22B outperforms in 0 benchmarks, while Grok-2 is better at 1 benchmark (HumanEval). Grok-2 significantly outperforms across most benchmarks.

Choose Codestral-22B if…

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

Choose Grok-2 if…

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • you want the most recent training data — it shipped Aug 2024

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Codestral-22B outperforms in 0 benchmarks, while Grok-2 is better at 1 benchmark (HumanEval).

Grok-2 significantly outperforms across most benchmarks.

Wed Jul 15 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Grok-2 specifies input context (128,000 tokens). Only Grok-2 specifies output context (8,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
xAI
Grok-2
Input128,000 tokens
Output8,000 tokens
Wed Jul 15 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Grok-2 supports multimodal inputs, whereas Codestral-22B does not.

Grok-2 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Grok-2

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Grok-2 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-2

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Grok-2 was released on 2024-08-13.

Grok-2 is 3 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.1 years ago

Grok-2

Aug 13, 2024

1.9 years ago

2mo 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
Has open weights
xAI
Larger context window (128,000 tokens)
Supports multimodal inputs
Higher HumanEval score (88.4% vs 81.1%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Codestral-22B and Grok-2 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Grok-2
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
xAI
Grok-2

FAQ

Common questions about Codestral-22B vs Grok-2.

Which is better, Codestral-22B or Grok-2?

Grok-2 significantly outperforms across most benchmarks. Codestral-22B is made by Mistral AI and Grok-2 is made by xAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Codestral-22B compare to Grok-2 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Grok-2 scores DocVQA: 93.6%, HumanEval: 88.4%, MMLU: 87.5%, MATH: 76.1%, MMLU-Pro: 75.5%.

What are the context window sizes for Codestral-22B and Grok-2?

Codestral-22B supports an unknown number of tokens and Grok-2 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 Grok-2?

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-2?

Codestral-22B is developed by Mistral AI and Grok-2 is developed by xAI.

Related comparisons