Model Comparison

Gemini 1.5 Flash vs Codestral-22B

Codestral-22B significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Gemini 1.5 Flash outperforms in 0 benchmarks, while Codestral-22B is better at 1 benchmark (HumanEval).

Codestral-22B significantly outperforms across most benchmarks.

Tue May 05 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Gemini 1.5 Flash specifies input context (1,048,576 tokens). Only Gemini 1.5 Flash specifies output context (8,192 tokens).

Google
Gemini 1.5 Flash
Input1,048,576 tokens
Output8,192 tokens
Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Tue May 05 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemini 1.5 Flash supports multimodal inputs, whereas Codestral-22B does not.

Gemini 1.5 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemini 1.5 Flash

Text
Images
Audio
Video

Codestral-22B

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 1.5 Flash is licensed under a proprietary license, while Codestral-22B uses MNPL-0.1.

License differences may affect how you can use these models in commercial or open-source projects.

Gemini 1.5 Flash

Proprietary

Closed source

Codestral-22B

MNPL-0.1

Open weights

Release Timeline

When each model was launched

Gemini 1.5 Flash was released on 2024-05-01, while Codestral-22B was released on 2024-05-29.

Codestral-22B is 1 month newer than Gemini 1.5 Flash.

Gemini 1.5 Flash

May 1, 2024

2.0 years ago

Codestral-22B

May 29, 2024

1.9 years ago

4w newer

Knowledge Cutoff

When training data ends

Gemini 1.5 Flash has a documented knowledge cutoff of 2023-11-01, while Codestral-22B's cutoff date is not specified.

We can confirm Gemini 1.5 Flash's training data extends to 2023-11-01, but cannot make a direct comparison without Codestral-22B's cutoff date.

Gemini 1.5 Flash

Nov 2023

Codestral-22B

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (1,048,576 tokens)
Supports multimodal inputs
Mistral AI
Has open weights
Higher HumanEval score (81.1% vs 74.3%)
GoogleGemini 1.5 Flash
Mistral AICodestral-22B
Compare in Playground

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemini 1.5 Flash
Mistral AI
Codestral-22B

FAQ

Common questions about Gemini 1.5 Flash vs Codestral-22B.

Which is better, Gemini 1.5 Flash or Codestral-22B?

Codestral-22B significantly outperforms across most benchmarks. Gemini 1.5 Flash is made by Google and Codestral-22B is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemini 1.5 Flash compare to Codestral-22B in benchmarks?

Gemini 1.5 Flash scores XSTest: 97.0%, HellaSwag: 86.5%, GSM8k: 86.2%, BIG-Bench Hard: 85.5%, MGSM: 82.6%. Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%.

What are the context window sizes for Gemini 1.5 Flash and Codestral-22B?

Gemini 1.5 Flash supports 1.0M tokens and Codestral-22B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemini 1.5 Flash and Codestral-22B?

Key differences include multimodal support (yes vs no), licensing (Proprietary vs MNPL-0.1). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 1.5 Flash and Codestral-22B?

Gemini 1.5 Flash is developed by Google and Codestral-22B is developed by Mistral AI.