Gemma 2 27B vs Qwen2.5 32B Instruct Comparison

Comparing Gemma 2 27B and Qwen2.5 32B Instruct across benchmarks, pricing, and capabilities.

Performance Benchmarks

Comparative analysis across standard metrics

8 benchmarks

Gemma 2 27B outperforms in 3 benchmarks (ARC-C, HellaSwag, Winogrande), while Qwen2.5 32B Instruct is better at 5 benchmarks (GSM8k, HumanEval, MATH, MBPP, MMLU).

Qwen2.5 32B Instruct shows notably better performance in the majority of benchmarks.

Mon Mar 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Mon Mar 16 2026 • llm-stats.com
Google
Gemma 2 27B
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Alibaba Cloud / Qwen Team
Qwen2.5 32B Instruct
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

5.3B diff

Qwen2.5 32B Instruct has 5.3B more parameters than Gemma 2 27B, making it 19.5% larger.

Google
Gemma 2 27B
27.2Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5 32B Instruct
32.5Bparameters
27.2B
Gemma 2 27B
32.5B
Qwen2.5 32B Instruct

License

Usage and distribution terms

Gemma 2 27B is licensed under Gemma, while Qwen2.5 32B Instruct uses Apache 2.0.

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

Gemma 2 27B

Gemma

Open weights

Qwen2.5 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemma 2 27B was released on 2024-06-27, while Qwen2.5 32B Instruct was released on 2024-09-19.

Qwen2.5 32B Instruct is 3 months newer than Gemma 2 27B.

Gemma 2 27B

Jun 27, 2024

1.7 years ago

Qwen2.5 32B Instruct

Sep 19, 2024

1.5 years ago

2mo 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

Higher ARC-C score (71.4% vs 70.4%)
Higher HellaSwag score (86.4% vs 85.2%)
Higher Winogrande score (83.7% vs 82.0%)
Alibaba Cloud / Qwen Team

Qwen2.5 32B Instruct

View details

Alibaba Cloud / Qwen Team

Higher GSM8k score (95.9% vs 74.0%)
Higher HumanEval score (88.4% vs 51.8%)
Higher MATH score (83.1% vs 42.3%)
Higher MBPP score (84.0% vs 62.6%)
Higher MMLU score (83.3% vs 75.2%)

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemma 2 27B
Alibaba Cloud / Qwen Team
Qwen2.5 32B Instruct