Model Comparison
Codestral-22B vs Hy3Which is better in 2026?
Comparing Codestral-22B and Hy3 across benchmarks, pricing, and capabilities.
Verdict: Codestral-22B vs Hy3 — which is better?
Codestral-22B (by Mistral AI) and Hy3 (by Tencent) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
Choose Codestral-22B if…
- you are already invested in the Mistral AI ecosystem
Choose Hy3 if…
- you want the most recent training data — it shipped Jul 2026
Performance Benchmarks
Comparative analysis across standard metrics
Codestral-22B and Hy3don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Arena Performance
Human preference votes
Model Size
Parameter count comparison
Hy3 has 272.8B more parameters than Codestral-22B, making it 1228.8% larger.
License
Usage and distribution terms
Codestral-22B is licensed under MNPL-0.1, while Hy3 uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
MNPL-0.1
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Codestral-22B was released on 2024-05-29, while Hy3 was released on 2026-07-06.
Hy3 is 26 months newer than Codestral-22B.
May 29, 2024
2.1 years ago
Jul 6, 2026
1 weeks ago
2.1yr newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Outputs Comparison
Key Takeaways
Codestral-22B
View detailsMistral AI
No standout differentiators in the data we have for this pair.
Hy3
View detailsTencent
No standout differentiators in the data we have for this pair.
Detailed Comparison
Interactive Arena
Judge for yourself.
Run your own prompts against Codestral-22B and Hy3 side-by-side, then vote on the output you prefer.
| Feature |
|---|
FAQ
Common questions about Codestral-22B vs Hy3.