The AI arena is free today

Open Superagent

Codestral-22B vs Qwen2-VL-72B-Instruct

Qwen2-VL-72B-Instruct leads the LLM Stats Score 14.6 to 0.2.

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

Which is better?

Qwen2-VL-72B-Instruct leads the overall LLM Stats Score 14.6 to 0.2, ranking #219 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 Qwen2-VL-72B-Instruct

  • overall performance matters — it scores 14.6 and ranks #219 on LLM Stats
  • you want the most recent training data — it shipped Aug 2024

At a glance

The differences that matter most.

Core performance indexes
0.2
#309
14.6
#219
0.1
#303
11.9
#235
Cost, coverage & limits
Benchmark wins
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Individual benchmarks

7 reported for Codestral-22B · 15 for Qwen2-VL-72B-Instruct

No common benchmarks found

Codestral-22B and Qwen2-VL-72B-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

51.2B diff

Qwen2-VL-72B-Instruct has 51.2B more parameters than Codestral-22B, making it 230.6% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Alibaba Cloud / Qwen Team
Qwen2-VL-72B-Instruct
73.4Bparameters
22.2B
Codestral-22B
73.4B
Qwen2-VL-72B-Instruct

Input capabilities

Documented input modalities across available providers

Qwen2-VL-72B-Instruct supports multimodal inputs, whereas Codestral-22B does not.

Qwen2-VL-72B-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-VL-72B-Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Codestral-22B is licensed under MNPL-0.1, while Qwen2-VL-72B-Instruct uses tongyi-qianwen.

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

Codestral-22B

MNPL-0.1

Open weights

Qwen2-VL-72B-Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Qwen2-VL-72B-Instruct was released on 2024-08-29.

Qwen2-VL-72B-Instruct is 3 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.3 years ago

Qwen2-VL-72B-Instruct

Aug 29, 2024

2.0 years ago

3mo newer

Knowledge Cutoff

When training data ends

Qwen2-VL-72B-Instruct has a documented knowledge cutoff of 2023-06-30, while Codestral-22B's cutoff date is not specified.

We can confirm Qwen2-VL-72B-Instruct's training data extends to 2023-06-30, but cannot make a direct comparison without Codestral-22B's cutoff date.

Codestral-22B

Qwen2-VL-72B-Instruct

Jun 2023

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Codestral-22B and Qwen2-VL-72B-Instruct side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Qwen2-VL-72B-Instruct
Open in Playground

FAQ

Common questions about Codestral-22B vs Qwen2-VL-72B-Instruct.

Which is better, Codestral-22B or Qwen2-VL-72B-Instruct?

Qwen2-VL-72B-Instruct leads the LLM Stats Score 14.6 to 0.2. Codestral-22B is made by Mistral AI and Qwen2-VL-72B-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 Qwen2-VL-72B-Instruct in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Qwen2-VL-72B-Instruct scores DocVQAtest: 96.5%, VCR_en_easy: 91.9%, ChartQA: 88.3%, OCRBench: 87.7%, MMBench: 86.5%.

What are the main differences between Codestral-22B and Qwen2-VL-72B-Instruct?

Key differences include LLM Stats Score (0.2 vs 14.6), multimodal support (no vs yes), licensing (MNPL-0.1 vs tongyi-qianwen). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Qwen2-VL-72B-Instruct?

Codestral-22B is developed by Mistral AI and Qwen2-VL-72B-Instruct is developed by Alibaba Cloud / Qwen Team.