Comprehensive side-by-side LLM comparison
Codestral 22B leads with 5.2% higher average benchmark score. Gemma 3 12B supports multimodal inputs. Overall, Codestral 22B is the stronger choice for coding tasks.
Mistral AI
Codestral is a 22-billion-parameter code-specialized model from Mistral AI, released in May 2024 as the company's first dedicated coding model, trained with focus on fill-in-the-middle (FIM) completion, code generation, and repair across 80+ programming languages. Unlike Mistral's general-purpose Apache 2.0 models, Codestral was released under a separate non-production research license, reflecting its positioning as a professional coding tool requiring commercial API access for production deployment. Its FIM support made it particularly valued for IDE integrations and code completion tools that need to insert code within existing contexts rather than only appending to the end.
Google DeepMind
Gemma 3 12B is a 12-billion-parameter open-weight model from Google DeepMind, released in March 2025 as part of the Gemma 3 series designed to bring multimodal reasoning to accessible hardware. The model supports both text and image inputs across a 128K token context window, extending the vision capabilities that defined the Gemma 3 generation compared to earlier text-only Gemma releases. It became widely adopted for domain-specific fine-tuning in research and enterprise settings where full multimodal capability was needed without the infrastructure demands of larger frontier models.
9 months newer

Codestral 22B
Mistral AI
2024-05-29

Gemma 3 12B
Google DeepMind
2025-03-12
Average performance across 1 common benchmarks
Codestral 22B
Gemma 3 12B
Performance comparison across key benchmark categories
Codestral 22B
Gemma 3 12B
Available providers and their performance metrics
Codestral 22B
Gemma 3 12B
Codestral 22B
Gemma 3 12B