Model Comparison

Codestral-22B vs Qwen2.5 VL 32B InstructWhich is better in 2026?

Qwen2.5 VL 32B Instruct significantly outperforms across most benchmarks.

Verdict: Codestral-22B vs Qwen2.5 VL 32B Instruct — which is better?

Codestral-22B (by Mistral AI) and Qwen2.5 VL 32B Instruct (by Alibaba Cloud / Qwen Team) 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.

Codestral-22B outperforms in 0 benchmarks, while Qwen2.5 VL 32B Instruct is better at 2 benchmarks (HumanEval, MBPP). Qwen2.5 VL 32B Instruct significantly outperforms across most benchmarks.

Choose Codestral-22B if…

  • you are already invested in the Mistral AI ecosystem

Choose Qwen2.5 VL 32B Instruct if…

  • you want the strongest raw capability — it leads on 2 of 2 shared benchmarks
  • you want the most recent training data — it shipped Feb 2025

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

Codestral-22B outperforms in 0 benchmarks, while Qwen2.5 VL 32B Instruct is better at 2 benchmarks (HumanEval, MBPP).

Qwen2.5 VL 32B Instruct significantly outperforms across most benchmarks.

Wed Jul 15 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

11.3B diff

Qwen2.5 VL 32B Instruct has 11.3B more parameters than Codestral-22B, making it 50.9% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5 VL 32B Instruct
33.5Bparameters
22.2B
Codestral-22B
33.5B
Qwen2.5 VL 32B Instruct

Input Capabilities

Supported data types and modalities

Qwen2.5 VL 32B Instruct supports multimodal inputs, whereas Codestral-22B does not.

Qwen2.5 VL 32B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Qwen2.5 VL 32B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Qwen2.5 VL 32B Instruct uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Codestral-22B

MNPL-0.1

Open weights

Qwen2.5 VL 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Qwen2.5 VL 32B Instruct was released on 2025-02-28.

Qwen2.5 VL 32B Instruct is 9 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.1 years ago

Qwen2.5 VL 32B Instruct

Feb 28, 2025

1.4 years ago

9mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

No standout differentiators in the data we have for this pair.

Alibaba Cloud / Qwen Team

Qwen2.5 VL 32B Instruct

View details

Alibaba Cloud / Qwen Team

Supports multimodal inputs
Higher HumanEval score (91.5% vs 81.1%)
Higher MBPP score (84.0% vs 78.2%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Codestral-22B and Qwen2.5 VL 32B Instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Qwen2.5 VL 32B Instruct
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Codestral-22B
Alibaba Cloud / Qwen Team
Qwen2.5 VL 32B Instruct

FAQ

Common questions about Codestral-22B vs Qwen2.5 VL 32B Instruct.

Which is better, Codestral-22B or Qwen2.5 VL 32B Instruct?

Qwen2.5 VL 32B Instruct significantly outperforms across most benchmarks. Codestral-22B is made by Mistral AI and Qwen2.5 VL 32B Instruct is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Codestral-22B compare to Qwen2.5 VL 32B Instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Qwen2.5 VL 32B Instruct scores DocVQA: 94.8%, Android Control Low_EM: 93.3%, HumanEval: 91.5%, ScreenSpot: 88.5%, MBPP: 84.0%.

What are the main differences between Codestral-22B and Qwen2.5 VL 32B Instruct?

Key differences include multimodal support (no vs yes), licensing (MNPL-0.1 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Qwen2.5 VL 32B Instruct?

Codestral-22B is developed by Mistral AI and Qwen2.5 VL 32B Instruct is developed by Alibaba Cloud / Qwen Team.