Model Comparison

Phi 4 Mini Reasoning vs Qwen2.5 32B Instruct

Phi 4 Mini Reasoning significantly outperforms across most benchmarks.

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Phi 4 Mini Reasoning outperforms in 1 benchmarks (GPQA), while Qwen2.5 32B Instruct is better at 0 benchmarks.

Phi 4 Mini Reasoning significantly outperforms across most benchmarks.

Fri Apr 17 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
Fri Apr 17 2026 • llm-stats.com
Microsoft
Phi 4 Mini Reasoning
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

28.7B diff

Qwen2.5 32B Instruct has 28.7B more parameters than Phi 4 Mini Reasoning, making it 755.3% larger.

Microsoft
Phi 4 Mini Reasoning
3.8Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5 32B Instruct
32.5Bparameters
3.8B
Phi 4 Mini Reasoning
32.5B
Qwen2.5 32B Instruct

License

Usage and distribution terms

Phi 4 Mini Reasoning is licensed under MIT, 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.

Phi 4 Mini Reasoning

MIT

Open weights

Qwen2.5 32B Instruct

Apache 2.0

Open weights

Release Timeline

When each model was launched

Phi 4 Mini Reasoning was released on 2025-04-30, while Qwen2.5 32B Instruct was released on 2024-09-19.

Phi 4 Mini Reasoning is 7 months newer than Qwen2.5 32B Instruct.

Phi 4 Mini Reasoning

Apr 30, 2025

11 months ago

7mo newer
Qwen2.5 32B Instruct

Sep 19, 2024

1.6 years ago

Knowledge Cutoff

When training data ends

Phi 4 Mini Reasoning has a documented knowledge cutoff of 2025-02-01, while Qwen2.5 32B Instruct's cutoff date is not specified.

We can confirm Phi 4 Mini Reasoning's training data extends to 2025-02-01, but cannot make a direct comparison without Qwen2.5 32B Instruct's cutoff date.

Phi 4 Mini Reasoning

Feb 2025

Qwen2.5 32B Instruct

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Higher GPQA score (52.0% vs 49.5%)
Alibaba Cloud / Qwen Team

Qwen2.5 32B Instruct

View details

Alibaba Cloud / Qwen Team

Detailed Comparison

AI Model Comparison Table
Feature
Microsoft
Phi 4 Mini Reasoning
Alibaba Cloud / Qwen Team
Qwen2.5 32B Instruct

FAQ

Common questions about Phi 4 Mini Reasoning vs Qwen2.5 32B Instruct

Phi 4 Mini Reasoning significantly outperforms across most benchmarks. Phi 4 Mini Reasoning is made by Microsoft and Qwen2.5 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.
Phi 4 Mini Reasoning scores MATH-500: 94.6%, AIME: 57.5%, GPQA: 52.0%. Qwen2.5 32B Instruct scores GSM8k: 95.9%, HumanEval: 88.4%, HellaSwag: 85.2%, BBH: 84.5%, MBPP: 84.0%.
Key differences include licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Phi 4 Mini Reasoning is developed by Microsoft and Qwen2.5 32B Instruct is developed by Alibaba Cloud / Qwen Team.