Model Comparison

DeepSeek VL2 Tiny vs Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

7 benchmarks

DeepSeek VL2 Tiny outperforms in 0 benchmarks, while Qwen2.5 VL 72B Instruct is better at 7 benchmarks (AI2D, ChartQA, DocVQA, MMBench, MMMU, MMStar, OCRBench).

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.

Fri May 15 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

69.0B diff

Qwen2.5 VL 72B Instruct has 69.0B more parameters than DeepSeek VL2 Tiny, making it 2300.0% larger.

DeepSeek VL2 Tiny

3.0Bparameters

Qwen2.5 VL 72B Instruct

72.0Bparameters

3.0B

DeepSeek VL2 Tiny

72.0B

Qwen2.5 VL 72B Instruct

Input Capabilities

Supported data types and modalities

Both DeepSeek VL2 Tiny and Qwen2.5 VL 72B Instruct support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

DeepSeek VL2 Tiny

Text

Images

Audio

Video

Qwen2.5 VL 72B Instruct

Text

Images

Audio

Video

License

Usage and distribution terms

DeepSeek VL2 Tiny is licensed under deepseek, while Qwen2.5 VL 72B Instruct uses tongyi-qianwen.

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

DeepSeek VL2 Tiny

deepseek

Open weights

Qwen2.5 VL 72B Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

DeepSeek VL2 Tiny was released on 2024-12-13, while Qwen2.5 VL 72B Instruct was released on 2025-01-26.

Qwen2.5 VL 72B Instruct is 1 month newer than DeepSeek VL2 Tiny.

DeepSeek VL2 Tiny

Dec 13, 2024

1.4 years ago

Qwen2.5 VL 72B Instruct

Jan 26, 2025

1.3 years ago

1mo 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

DeepSeek VL2 Tiny

View details

DeepSeek

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

Qwen2.5 VL 72B Instruct

View details

Alibaba Cloud / Qwen Team

Higher AI2D score (88.4% vs 71.6%)

Higher ChartQA score (89.5% vs 81.0%)

Higher DocVQA score (96.4% vs 88.9%)

Higher MMBench score (88.0% vs 69.2%)

Higher MMMU score (70.2% vs 40.7%)

Higher MMStar score (70.8% vs 45.9%)

Higher OCRBench score (88.5% vs 80.9%)

Detailed Comparison

AI Model Comparison Table
Feature	DeepSeek VL2 Tiny	Qwen2.5 VL 72B Instruct

FAQ

Common questions about DeepSeek VL2 Tiny vs Qwen2.5 VL 72B Instruct.

Which is better, DeepSeek VL2 Tiny or Qwen2.5 VL 72B Instruct?

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks. DeepSeek VL2 Tiny is made by DeepSeek and Qwen2.5 VL 72B 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 DeepSeek VL2 Tiny compare to Qwen2.5 VL 72B Instruct in benchmarks?

DeepSeek VL2 Tiny scores DocVQA: 88.9%, ChartQA: 81.0%, OCRBench: 80.9%, TextVQA: 80.7%, AI2D: 71.6%. Qwen2.5 VL 72B Instruct scores DocVQA: 96.4%, Android Control Low_EM: 93.7%, ChartQA: 89.5%, OCRBench: 88.5%, AI2D: 88.4%.

What are the main differences between DeepSeek VL2 Tiny and Qwen2.5 VL 72B Instruct?

Key differences include licensing (deepseek vs tongyi-qianwen). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek VL2 Tiny and Qwen2.5 VL 72B Instruct?

DeepSeek VL2 Tiny is developed by DeepSeek and Qwen2.5 VL 72B Instruct is developed by Alibaba Cloud / Qwen Team.