Model Comparison
QvQ-72B-Preview vs Qwen3 VL 30B A3B ThinkingWhich is better in 2026?
Qwen3 VL 30B A3B Thinking significantly outperforms across most benchmarks.
Verdict: QvQ-72B-Preview vs Qwen3 VL 30B A3B Thinking — which is better?
QvQ-72B-Preview (by Alibaba Cloud / Qwen Team) and Qwen3 VL 30B A3B Thinking (by Alibaba Cloud / Qwen Team) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
QvQ-72B-Preview outperforms in 0 benchmarks, while Qwen3 VL 30B A3B Thinking is better at 1 benchmark (MathVision). Qwen3 VL 30B A3B Thinking significantly outperforms across most benchmarks.
Choose QvQ-72B-Preview if…
- you are already invested in the Alibaba Cloud / Qwen Team ecosystem
Choose Qwen3 VL 30B A3B Thinking if…
- you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
- you want the most recent training data — it shipped Sep 2025
Performance Benchmarks
Comparative analysis across standard metrics
QvQ-72B-Preview outperforms in 0 benchmarks, while Qwen3 VL 30B A3B Thinking is better at 1 benchmark (MathVision).
Qwen3 VL 30B A3B Thinking significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Model Size
Parameter count comparison
QvQ-72B-Preview has 42.4B more parameters than Qwen3 VL 30B A3B Thinking, making it 136.8% larger.
Context Window
Maximum input and output token capacity
Only Qwen3 VL 30B A3B Thinking specifies input context (131,072 tokens). Only Qwen3 VL 30B A3B Thinking specifies output context (32,768 tokens).
Input Capabilities
Supported data types and modalities
Both QvQ-72B-Preview and Qwen3 VL 30B A3B Thinking support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
QvQ-72B-Preview
Qwen3 VL 30B A3B Thinking
License
Usage and distribution terms
QvQ-72B-Preview is licensed under Qwen, while Qwen3 VL 30B A3B Thinking uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Qwen
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
QvQ-72B-Preview was released on 2024-12-25, while Qwen3 VL 30B A3B Thinking was released on 2025-09-22.
Qwen3 VL 30B A3B Thinking is 9 months newer than QvQ-72B-Preview.
Dec 25, 2024
1.4 years ago
Sep 22, 2025
8 months ago
9mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Outputs Comparison
Key Takeaways
QvQ-72B-Preview
View detailsAlibaba Cloud / Qwen Team
No standout differentiators in the data we have for this pair.
Qwen3 VL 30B A3B Thinking
View detailsAlibaba Cloud / Qwen Team
Detailed Comparison
| Feature | | |
|---|
FAQ
Common questions about QvQ-72B-Preview vs Qwen3 VL 30B A3B Thinking.