Model Comparison

Gemma 3n E2B Instructed vs Qwen2.5 VL 32B Instruct

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

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Gemma 3n E2B Instructed outperforms in 0 benchmarks, while Qwen2.5 VL 32B Instruct is better at 5 benchmarks (GPQA, HumanEval, MBPP, MMLU, MMLU-Pro).

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

Sat May 02 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

25.5B diff

Qwen2.5 VL 32B Instruct has 25.5B more parameters than Gemma 3n E2B Instructed, making it 318.8% larger.

Gemma 3n E2B Instructed

8.0Bparameters

Qwen2.5 VL 32B Instruct

33.5Bparameters

8.0B

Gemma 3n E2B Instructed

33.5B

Qwen2.5 VL 32B Instruct

Input Capabilities

Supported data types and modalities

Both Gemma 3n E2B Instructed and Qwen2.5 VL 32B Instruct support multimodal inputs.

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

Gemma 3n E2B Instructed

Text

Images

Audio

Video

Qwen2.5 VL 32B Instruct

Text

Images

Audio

Video

License

Usage and distribution terms

Gemma 3n E2B Instructed is licensed under a proprietary license, 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.

Gemma 3n E2B Instructed

Proprietary

Closed source

Qwen2.5 VL 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemma 3n E2B Instructed was released on 2025-06-26, while Qwen2.5 VL 32B Instruct was released on 2025-02-28.

Gemma 3n E2B Instructed is 4 months newer than Qwen2.5 VL 32B Instruct.

Gemma 3n E2B Instructed

Jun 26, 2025

10 months ago

3mo newer

Qwen2.5 VL 32B Instruct

Feb 28, 2025

1.2 years ago

Knowledge Cutoff

When training data ends

Gemma 3n E2B Instructed has a documented knowledge cutoff of 2024-06-01, while Qwen2.5 VL 32B Instruct's cutoff date is not specified.

We can confirm Gemma 3n E2B Instructed's training data extends to 2024-06-01, but cannot make a direct comparison without Qwen2.5 VL 32B Instruct's cutoff date.

Gemma 3n E2B Instructed

Jun 2024

Qwen2.5 VL 32B Instruct

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Gemma 3n E2B Instructed

View details

Google

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

Qwen2.5 VL 32B Instruct

View details

Alibaba Cloud / Qwen Team

Has open weights

Higher GPQA score (46.0% vs 24.8%)

Higher HumanEval score (91.5% vs 66.5%)

Higher MBPP score (84.0% vs 56.6%)

Higher MMLU score (78.4% vs 60.1%)

Higher MMLU-Pro score (68.8% vs 40.5%)

Detailed Comparison

AI Model Comparison Table
Feature	Gemma 3n E2B Instructed	Qwen2.5 VL 32B Instruct

FAQ

Common questions about Gemma 3n E2B Instructed vs Qwen2.5 VL 32B Instruct.

Which is better, Gemma 3n E2B Instructed or Qwen2.5 VL 32B Instruct?

Qwen2.5 VL 32B Instruct significantly outperforms across most benchmarks. Gemma 3n E2B Instructed is made by Google 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 Gemma 3n E2B Instructed compare to Qwen2.5 VL 32B Instruct in benchmarks?

Gemma 3n E2B Instructed scores HumanEval: 66.5%, MMLU: 60.1%, Global-MMLU-Lite: 59.0%, MBPP: 56.6%, Global-MMLU: 55.1%. 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 Gemma 3n E2B Instructed and Qwen2.5 VL 32B Instruct?

Key differences include licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 3n E2B Instructed and Qwen2.5 VL 32B Instruct?

Gemma 3n E2B Instructed is developed by Google and Qwen2.5 VL 32B Instruct is developed by Alibaba Cloud / Qwen Team.