Model Comparison

Codestral-22B vs Gemini 1.0 ProWhich is better in 2026?

Comparing Codestral-22B and Gemini 1.0 Pro across benchmarks, pricing, and capabilities.

Verdict: Codestral-22B vs Gemini 1.0 Pro — which is better?

Codestral-22B (by Mistral AI) and Gemini 1.0 Pro (by Google) 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 want the most recent training data — it shipped May 2024
  • you need open weights you can self-host or fine-tune

Choose Gemini 1.0 Pro if…

  • you want predictable pricing at $0.50/M input and $1.50/M output
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

No common benchmarks found

Codestral-22B and Gemini 1.0 Prodon'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 Gemini 1.0 Pro specifies input context (32,760 tokens). Only Gemini 1.0 Pro specifies output context (8,192 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Google
Gemini 1.0 Pro
Input32,760 tokens
Output8,192 tokens
Tue Jun 23 2026 • llm-stats.com

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Gemini 1.0 Pro 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

Gemini 1.0 Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Gemini 1.0 Pro was released on 2024-02-15.

Codestral-22B is 3 months newer than Gemini 1.0 Pro.

Codestral-22B

May 29, 2024

2.1 years ago

3mo newer
Gemini 1.0 Pro

Feb 15, 2024

2.4 years ago

Knowledge Cutoff

When training data ends

Gemini 1.0 Pro has a documented knowledge cutoff of 2024-02-01, while Codestral-22B's cutoff date is not specified.

We can confirm Gemini 1.0 Pro's training data extends to 2024-02-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

—

Gemini 1.0 Pro

Feb 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Mistral AI
Has open weights
Google
Larger context window (32,760 tokens)

Detailed Comparison

AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
Google
Gemini 1.0 Pro

FAQ

Common questions about Codestral-22B vs Gemini 1.0 Pro.

Which is better, Codestral-22B or Gemini 1.0 Pro?

Codestral-22B (Mistral AI) and Gemini 1.0 Pro (Google) 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 Gemini 1.0 Pro in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Gemini 1.0 Pro scores FLEURS: 93.6%, BIG-Bench: 75.0%, MMLU: 71.8%, WMT23: 71.7%, EgoSchema: 55.7%.

What are the context window sizes for Codestral-22B and Gemini 1.0 Pro?

Codestral-22B supports an unknown number of tokens and Gemini 1.0 Pro supports 33K 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 Gemini 1.0 Pro?

Key differences include licensing (MNPL-0.1 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Gemini 1.0 Pro?

Codestral-22B is developed by Mistral AI and Gemini 1.0 Pro is developed by Google.

Related comparisons