Codestral-22B vs Gemma 2 9B
Codestral-22B significantly outperforms across most benchmarks.
Mistral AI · Google · Updated for 2026
Which is better?
Codestral-22B outperforms in 2 benchmarks (HumanEval, MBPP), while Gemma 2 9B is better at 0 benchmarks. Codestral-22B significantly outperforms across most benchmarks.
Based on current benchmark, pricing, and model metadata for 2026.
Choose Codestral-22B
- you want the strongest raw capability — it leads on 2 of 2 shared benchmarks
Choose Gemma 2 9B
- you want the most recent training data — it shipped Jun 2024
At a glance
The differences that matter most.
Performance Benchmarks
Comparative analysis across standard metrics
Codestral-22B outperforms in 2 benchmarks (HumanEval, MBPP), while Gemma 2 9B is better at 0 benchmarks.
Codestral-22B significantly outperforms across most benchmarks.
Arena Performance
Playground indexes and blind preference scores
Model Size
Parameter count comparison
Codestral-22B has 13.0B more parameters than Gemma 2 9B, making it 140.3% larger.
License
Usage and distribution terms
Codestral-22B is licensed under MNPL-0.1, while Gemma 2 9B uses Gemma.
License differences may affect how you can use these models in commercial or open-source projects.
MNPL-0.1
Open weights
Gemma
Open weights
Release Timeline
When each model was launched
Codestral-22B was released on 2024-05-29, while Gemma 2 9B was released on 2024-06-27.
Gemma 2 9B is 1 month newer than Codestral-22B.
May 29, 2024
2.2 years ago
Jun 27, 2024
2.2 years ago
4w newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Outputs Comparison
Judge for yourself.
Run your own prompts against Codestral-22B and Gemma 2 9B side-by-side, then vote on the output you prefer.
FAQ
Common questions about Codestral-22B vs Gemma 2 9B.