---
title: Biomni-R0-32B-Preview
description: "Biomni-R0-32B-Preview is a biomedical AI agent model from Stanford (Leskovec lab): Qwen3-32B trained by multi-turn reinforcement learning inside the Biomni environment. It is meant to run with the Biomni agent and its tools (github.com/snap-stanford/biomni), not as a standalone chat model."
tags:
- agent
- biology
- biomedical
- code
- en
- qwen3
- reasoning
license: mit
source_url: https://huggingface.co/biomni/Biomni-R0-32B-Preview
---

# Biomni-R0-32B-Preview

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

Biomni-R0-32B-Preview is a biomedical AI agent model from Stanford (Leskovec lab): Qwen3-32B trained by multi-turn reinforcement learning inside the Biomni environment. It is meant to run with the Biomni agent and its tools (github.com/snap-stanford/biomni), not as a standalone chat model.

Upstream identifier: `biomni/Biomni-R0-32B-Preview`. Agent and tools: [snap-stanford/biomni](https://github.com/snap-stanford/biomni). Technical report: [biomni.stanford.edu/paper.pdf](https://biomni.stanford.edu/paper.pdf).

**Source:** https://huggingface.co/biomni/Biomni-R0-32B-Preview

**Licence:** mit

_This model is part of the Atlas demo catalogue. See the repository history for provenance._