Google bakes computer control directly into Gemini 3.5 Flash, letting the model see and operate your screen

Google has integrated “Computer Use” directly into Gemini 3.5 Flash, letting the model operate computers, browsers, and mobile devices on its own. On the OSWorld benchmark, it scores 78.4, putting it on par with GPT-5.5.

Previously, this was only available as a separate Gemini 2.5 model. Combined with existing tools like function calls, Search, and Maps, developers can now build agents that work across browser, mobile, and desktop environments for tasks like software testing or office automation. On the OSWorld benchmark, Gemini 3.5 Flash scores 78.4, beating Gemini 3 Flash (65.1) and GPT-5.4 mini (72.1). GPT-5.5 sits just ahead at 78.7, while Anthropic’s Opus 4.8 leads at 83.4. Sonnet 4.6 also hits 78.4, and Gemini 3.1 Pro lands at 76.2. To guard against prompt injection attacks, Google uses adversarial training and two optional enterprise safeguards. One requires user confirmation for sensitive or irreversible actions, while the other automatically stops tasks when it detects indirect prompt injections. Google also recommends sandboxing, human oversight, and strict access controls, with more details in its best practices documentation. The feature is available through the Gemini API and the Gemini Enterprise Agent Platform. A Browserbase demo and a GitHub reference implementation are also available.AdDEC_D_Incontent-1Ad Follow The Decoder for AI news, background stories and expert analyses.