gpt.buzz
Sign in

news

Gemma 4: Byte for byte, the most capable open models

April 3, 2026

Gemma 4 is Google's newest open model family, described as its most intelligent to date and purpose-built for advanced reasoning and agentic workflows. The release signals a push toward stronger open-weight models for tasks that require planning, tool use, and more autonomous behavior.

Gemma 4: Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows.

Source: deepmind.google

← All news

Gemma 4: Byte for byte, the most capable open models · gpt.buzz