Qwen2.5 72B Instruct vs Qwen Plus 0728 (thinking) (Comparative Analysis)
Loading comparison form...
Comparative Analysis: Qwen2.5 72B Instruct vs. Qwen Plus 0728 (thinking)
Want to try out these models side by side?Try Magica for free
Overview
Qwen2.5 72B Instruct was released 11 months before Qwen Plus 0728 (thinking).
 Qwen2.5 72B Instruct | Qwen Plus 0728 (thinking) | |
|---|---|---|
Model Provider The organization behind this AI's development | Qwen | Qwen |
Input Context Window Maximum input tokens this model can process at once | 131.1K tokens | 1M tokens |
Output Token Limit Maximum output tokens this model can generate at once | 16.4K tokens | 32.8K tokens |
Release Date When this model first became publicly available | September 19, 2024 1 year ago September 19th, 2024 | September 8, 2025 10 months ago September 8th, 2025 |
Capabilities & Features
Compare supported features, modalities, and advanced capabilities
Qwen2.5 72B Instruct | Qwen Plus 0728 (thinking) | |
|---|---|---|
Input Types Supported input formats | 📝Text | 📝Text |
Output Types Supported output formats | 📝Text | 📝Text |
Tokenizer Text encoding system | Qwen | Qwen3 |
Key Features Advanced capabilities | ✓Function Calling✓Structured OutputReasoning ModeContent Moderation | ✓Function Calling✓Structured Output✓Reasoning ModeContent Moderation |
Open Source Model availability | Available on HuggingFace → | Proprietary |
Pricing
Qwen2.5 72B Instruct is roughly 1.4x more expensive compared to Qwen Plus 0728 (thinking) for input tokens and roughly 0.5x less expensive for output tokens.
| Qwen2.5 72B Instruct | Qwen Plus 0728 (thinking) | |
|---|---|---|
Input Token Cost Cost per million input tokens | $0.36 per million tokens | $0.26 per million tokens |
Output Token Cost Cost per million outut tokens | $0.40 per million tokens | $0.78 per million tokens |
Benchmarks
Compare relevant benchmarks between Qwen2.5 72B Instruct and Qwen Plus 0728 (thinking).
| Qwen2.5 72B Instruct | Qwen Plus 0728 (thinking) | |
|---|---|---|
MMLU Measures knowledge across 57 subjects like law, math, history, and science | Benchmark not available. | Benchmark not available. |
MMMU Measures understanding of combined text and images across various domains | Benchmark not available. | Benchmark not available. |
HellaSwag Measures common sense reasoning by having models complete sentences about everyday situations | Benchmark not available. | Benchmark not available. |
At a Glance
Quick overview of what makes Qwen2.5 72B Instruct and Qwen Plus 0728 (thinking) unique.
Qwen2.5 72B Instruct by Qwen can use external tools and APIs, generates structured data. It can handle standard conversations with its 131.1K token context window. Very affordable at $0.36/M input and $0.40/M output tokens. Released September 19th, 2024.Qwen Plus 0728 (thinking) by Qwen can use external tools and APIs, offers advanced reasoning, generates structured data. It can handle standard conversations with its 1M token context window. Very affordable at $0.26/M input and $0.78/M output tokens. Released September 8th, 2025.Explore More Comparisons
Compare your models with top performers across different categories
Compare Qwen2.5 72B Instruct with:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
Compare Qwen Plus 0728 (thinking) with:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks