BenchMark'd
No ratings yet
Be the first to review this model
Mistral's code-specialized 22B model trained on 80+ programming languages, optimized for fill-in-the-middle completion, code correction, and test generation. Designed specifically for IDE integration and real-time coding assistance. A top choice for developers needing fast, accurate code completions across multiple languages.
Released
May 29, 2024
Parameters
22B
Context
32K
Pricing
Paid
Last updated: March 15, 2026
Benchmark scores may vary based on evaluation methodology and conditions.