---
format: "aidr-story-markdown/v1"
id: "d67fad11e3ef485535f8197eef24d1b7ed3ae9264bd1f87d6e44dcc1b6e56561"
canonical_url: "https://aidr.today/d67fad11?lang=en"
title: "Alibaba Releases Qwen Drive 1.0, First Autonomous Driving VLM"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-07T16:44:39.000Z"
category: "Models"
topics: ["alibaba","qwen","vision-language","open-source","gemma"]
source_urls: ["https://huggingnews.com/ai/alibaba-releases-qwen-drive-10-first-autonomous-driving-vlm-15beca59","https://x.com/techtechchina/status/2096944420587462955","https://x.com/askalphaxiv/status/2096981567579021456","https://x.com/eyishazyer/status/2096915052616106124"]
summary: "Qwen-Drive-1.0-4B is a 4B parameter vision-language model that unifies 3D perception, visual question and answering, and trajectory planning. Developed with Huazhong University of Science and Technology, the system uses a Qwen3.5-4B backbone with a BEV perception head and a flow-based Planning Expert. It posted a 69.43 average driving VQA score, beating the 58.15 score of the three times larger 12B Gemma4 model. Performance metrics include a 90.7 score on NAVSIM and 43.95 mAP on nuScenes. The release includes two planner versions, with a reinforcement learning variant that reduces the off-road rate by 50% by adopting more cautious weights. Alibaba released the code, weights, and demo data under an Apache 2.0 license."
---

# Alibaba Releases Qwen Drive 1\.0, First Autonomous Driving VLM

> [Open the canonical story](<https://aidr.today/d67fad11?lang=en>)

**Published:** 2026-09-07T16:44:39.000Z
**Category:** Models
**Topics:** alibaba, qwen, vision\-language, open\-source, gemma

## Summary

Qwen\-Drive\-1\.0\-4B is a 4B parameter vision\-language model that unifies 3D perception, visual question and answering, and trajectory planning\. Developed with Huazhong University of Science and Technology, the system uses a Qwen3\.5\-4B backbone with a BEV perception head and a flow\-based Planning Expert\. It posted a 69\.43 average driving VQA score, beating the 58\.15 score of the three times larger 12B Gemma4 model\. Performance metrics include a 90\.7 score on NAVSIM and 43\.95 mAP on nuScenes\. The release includes two planner versions, with a reinforcement learning variant that reduces the off\-road rate by 50% by adopting more cautious weights\. Alibaba released the code, weights, and demo data under an Apache 2\.0 license\.

## Sources

- [Story source](<https://huggingnews.com/ai/alibaba-releases-qwen-drive-10-first-autonomous-driving-vlm-15beca59>)
- [Story source](<https://x.com/techtechchina/status/2096944420587462955>)
- [Supporting source](<https://x.com/askalphaxiv/status/2096981567579021456>)
- [Supporting source](<https://x.com/eyishazyer/status/2096915052616106124>)