# Qwen releases QVQ-Max visual reasoning model

> Qwen released the first version of QVQ-Max, a visual reasoning model that accepts images and video as input and produces analysis and solutions. The announcement positions it as a successor to the QVQ-72B-Preview from December 2024, addressing earlier limitations.

| | |
|---|---|
| **Tool** | Qwen |
| **Version** | — |
| **Kind** | announcement |
| **Published** | 2025-03-27 |
| **Observed** | 2026-08-11 |
| **Significance** | 3/5 |
| **Breaking** | no |
| **Categories** | new-model, capability, model-support |

## What changed


- First official release of QVQ-Max, following the QVQ-72B-Preview exploratory model
- Model can understand and reason over images and video content
- Capabilities demonstrated across math problems, everyday questions, programming, and art


## Sources

- [blog_rss](https://qwenlm.github.io/blog/qvq-max-preview/) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/qwen/qwen-releases-qvq-max-visual-reasoning-model
Entity: https://changelogs.info/qwen
Event ID: `evt_2025-03-27_qwen_qvq-max-think-with-evidence`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.