The AI arena is free today

Open Superagent

Codestral-22B vs Qwen3 VL 32B Instruct

Qwen3 VL 32B Instruct leads the LLM Stats Score 20.4 to 0.1.

Mistral AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Qwen3 VL 32B Instruct leads the overall LLM Stats Score 20.4 to 0.1, ranking #193 overall.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Codestral-22B

  • you are already invested in the Mistral AI ecosystem

Choose Qwen3 VL 32B Instruct

  • overall performance matters — it scores 20.4 and ranks #193 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Sep 2025

At a glance

The differences that matter most.

Codestral-22B
Mistral AI
Qwen3 VL 32B Instruct
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
0.1
#324
20.4
#193
Reasoning
-0.1
#316
19.3
#199
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Individual benchmarks

7 reported for Codestral-22B · 45 for Qwen3 VL 32B Instruct

No common benchmarks found

Codestral-22B and Qwen3 VL 32B Instructdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

10.8B diff

Qwen3 VL 32B Instruct has 10.8B more parameters than Codestral-22B, making it 48.6% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
Qwen3 VL 32B Instruct
33.0Bparameters
22.2B
Codestral-22B
33.0B
Qwen3 VL 32B Instruct

Input capabilities

Documented input modalities across available providers

Qwen3 VL 32B Instruct supports multimodal inputs, whereas Codestral-22B does not.

Qwen3 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

Qwen3 VL 32B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Qwen3 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

Qwen3 VL 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Qwen3 VL 32B Instruct was released on 2025-09-22.

Qwen3 VL 32B Instruct is 16 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Qwen3 VL 32B Instruct

Sep 22, 2025

11 months ago

1.3yr 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→

Judge for yourself.

Run your own prompts against Codestral-22B and Qwen3 VL 32B Instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Qwen3 VL 32B Instruct
Open in Playground

FAQ

Common questions about Codestral-22B vs Qwen3 VL 32B Instruct.

Which is better, Codestral-22B or Qwen3 VL 32B Instruct?

Qwen3 VL 32B Instruct leads the LLM Stats Score 20.4 to 0.1. Codestral-22B is made by Mistral AI and Qwen3 VL 32B Instruct is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Qwen3 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%. Qwen3 VL 32B Instruct scores DocVQAtest: 96.9%, ScreenSpot: 95.8%, CharXiv-D: 90.5%, MMLU-Redux: 89.8%, AI2D: 89.5%.

What are the main differences between Codestral-22B and Qwen3 VL 32B Instruct?

Key differences include LLM Stats Score (0.1 vs 20.4), 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 Qwen3 VL 32B Instruct?

Codestral-22B is developed by Mistral AI and Qwen3 VL 32B Instruct is developed by Alibaba Cloud / Qwen Team.

Related comparisons