Frontier Radar

Microsoft's Mage-VL-Cowork is a 4B computer-use agent that both clicks and runs code, scoring 66.0% on OSWorld-Verified

· Week 2026-W44

Models

Get the weekly changelog Price changes and new agent features in one short email a week. Free, unsubscribe anytime.

Microsoft's Mage team released Mage-VL-Cowork, a 4B-parameter vision-language model that operates a desktop by clicking and typing from screenshots and, in the same task, running code and terminal commands. Microsoft reports 66.0% on OSWorld-Verified with a 50-step budget, ahead of larger open agents such as Qwen3.6-27B (63.9%) and EvoCUA-32B (56.7%), and says reinforcement learning cut model calls by 13.0% and output tokens by 25.4%. A model this small is aimed at computer-use agents that run on the device itself. The project page links the code on GitHub and the weights on Hugging Face.

Source

All Frontier Radar updates

The weekly agent builder changelog

One short email a week: which builder changed its prices or free plan, new agent features, and the frontier model updates that matter. Optional and free. Unsubscribe anytime. See a sample issue.

Emails are handled by beehiiv. Privacy · Prefer a file? Download the pricing sheet, no signup needed.