The AI arena is free today

Open Superagent

Codestral-22B vs Grok-3

Grok-3 leads the LLM Stats Score 30.8 to 0.2.

Mistral AI · xAI · Updated for 2026

Which is better?

Grok-3 leads the overall LLM Stats Score 30.8 to 0.2, ranking #105 overall.

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 Grok-3

  • overall performance matters — it scores 30.8 and ranks #105 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Feb 2025

At a glance

The differences that matter most.

Core performance indexes
0.2
#309
30.8
#105
0.1
#303
30.5
#105
2.5
#213
17.8
#106
Cost, coverage & limits
Benchmark wins
Input price
— / M
$3.00 / M
Output price
— / M
$15.00 / M
Context window
128,000

Individual benchmarks

7 reported for Codestral-22B · 5 for Grok-3

No common benchmarks found

Codestral-22B and Grok-3don'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

Context Window

Maximum input and output token capacity

Only Grok-3 specifies input context (128,000 tokens). Only Grok-3 specifies output context (8,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
xAI
Grok-3
Input128,000 tokens
Output8,000 tokens
Tue Sep 01 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Grok-3 supports multimodal inputs, whereas Codestral-22B does not.

Grok-3 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Grok-3

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Grok-3 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-3

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Grok-3 was released on 2025-02-17.

Grok-3 is 9 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Grok-3

Feb 17, 2025

1.5 years ago

8mo newer

Knowledge Cutoff

When training data ends

Grok-3 has a documented knowledge cutoff of 2024-11-17, while Codestral-22B's cutoff date is not specified.

We can confirm Grok-3's training data extends to 2024-11-17, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

Grok-3

Nov 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Codestral-22B and Grok-3 side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Grok-3
Open in Playground

FAQ

Common questions about Codestral-22B vs Grok-3.

Which is better, Codestral-22B or Grok-3?

Grok-3 leads the LLM Stats Score 30.8 to 0.2. Codestral-22B is made by Mistral AI and Grok-3 is made by xAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Grok-3 in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Grok-3 scores AIME 2024: 93.3%, AIME 2025: 93.3%, GPQA: 84.6%, LiveCodeBench: 79.4%, MMMU: 78.0%.

What are the context window sizes for Codestral-22B and Grok-3?

Codestral-22B supports an unknown number of tokens and Grok-3 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-3?

Key differences include LLM Stats Score (0.2 vs 30.8), 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-3?

Codestral-22B is developed by Mistral AI and Grok-3 is developed by xAI.