Codestral-22B

Unknown Developer

This powerful 22 billion parameter AI model excels at generating code in over 80 programming languages, such as Python, Java, C++, and JavaScript. It's adept at both understanding and following instructions, as well as utilizing fill-in-the-middle (FIM) functionality. This makes it perfect for a wide range of code completion and generation tasks.

Model Specifications

Technical details and capabilities of Codestral-22B

Core Specifications

22.2B Parameters

Model size and complexity

32.8K / 32.8K

Input / Output tokens

May 28, 2024

Release date

Capabilities & License

Multimodal Support
Not Supported
Web Hydrated
No
License
MNPL-0.1

Resources

API Reference
https://docs.mistral.ai/api/
Playground
https://chat.mistral.ai/

Performance Insights

Check out how Codestral-22B handles various AI tasks through comprehensive benchmark results.

100
75
50
25
0
91.6
HumanEvalFIM-Average
91.6
(92%)
81.1
HumanEval
81.1
(81%)
78.2
MBPP
78.2
(78%)
63.5
Spider
63.5
(64%)
61.5
HumanEval-Average
61.5
(62%)
51.3
CruxEval-O
51.3
(51%)
34
RepoBench
34
(34%)
HumanEvalFIM-Average
HumanEval
MBPP
Spider
HumanEval-Average
CruxEval-O
RepoBench

Detailed Benchmarks

Dive deeper into Codestral-22B's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Codestral-22B. Compare costs across platforms to find the best pricing for your use case.

OpenAI
Anthropic
Google
Mistral AI
Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models