Comprehensive side-by-side LLM comparison
Mistral Large 2 leads with 12.3% higher average benchmark score. Gemma 3 4B offers 6.1K more tokens in context window than Mistral Large 2. Gemma 3 4B is $7.94 cheaper per million tokens. Gemma 3 4B supports multimodal inputs. Overall, Mistral Large 2 is the stronger choice for coding tasks.
Gemma 3 4B was developed as a compact yet capable open-source model, designed to strike a balance between performance and resource efficiency. Built with 4 billion parameters and instruction tuning, it provides a practical option for applications requiring moderate capability with manageable computational costs.
Mistral AI
Mistral Large 2 was introduced as the second generation of Mistral's flagship model, designed to provide frontier-level capabilities across diverse language tasks. Built with enhanced reasoning, coding, and multilingual abilities, it represents Mistral's most advanced offering for enterprise and demanding applications.
7 months newer

Mistral Large 2
Mistral AI
2024-07-24

Gemma 3 4B
2025-03-12
Cost per million tokens (USD)

Gemma 3 4B

Mistral Large 2
Context window and performance specifications
Average performance across 2 common benchmarks

Gemma 3 4B

Mistral Large 2
Gemma 3 4B
2024-08-01
Available providers and their performance metrics

Gemma 3 4B
DeepInfra

Mistral Large 2

Gemma 3 4B

Mistral Large 2

Gemma 3 4B

Mistral Large 2
Mistral AI