NotebookLM rolling out big Gemini 3.5 & Antigravity upgrade with more outputs

Google is giving NotebookLM a big upgrade today across the underlying models, outputs, and research made possible by Gemini 3.5 and Antigravity.

NotebookLM now uses Gemini 3.5 and Antigravity — Google’s coding tool — to provide “even more accurate and reliable information along with better visibility into the thinking process.”

Each notebook now has a “secure cloud computer” that lets NotebookLM “write and run code useful for helping you perform deeper research and more complex analysis.”

The system includes more than 100 curated software skills, unlocking a wide range of new capabilities to help you more deeply understand the sources in your notebook.

This results in big upgrades compared to the prior system, according to side-by-side evaluations:

• “…the upgraded NotebookLM achieved an average win rate of over 65% — a 15% point margin above parity — across our top five core evaluation dimensions.”
• “…substantial improvements in large document analysis, securing a 69.9% win rate…”
• “…achieved exceptional performance in advanced web research and source discovery reaching a 78.2% win rate against our prior baseline.”

NotebookLM can now create outputs that are ready to download in more file formats:

• Data visualizations and charts: PNG, SVG
• Documents: PDFs, DOCX, Markdown, text files
• Images with Nano Banana: PNG, JPG, GIF
• Structured data: CSV, JSON
• Microsoft Excel: XLSX
• Microsoft PowerPoint: PPTX

You can provide detailed instructions, like creating PDF reports with charts and tables or detailed budget spreadsheets. After generation, you can request edits. More formats are coming in the future.

NotebookLM’s chat experience can now “guide you through building your source repository” if you’re starting a project with just “loose ideas and questions.”

Perhaps you want to find primary sources in other languages to better understand new perspectives, or you’re seeking related works by an author you recently discovered. It can even use Google Search to find relevant, high quality sources from the web and add them to your notebook.

Taken together, Google touts more workflows made possible in NotebookLM by these three core upgrades:

• Researchers: A data analyst can combine data from various countries with conflicting formatting. To make this information useful, the analyst can ask NotebookLM to conduct web research to find additional context, write code to perform accurate data analysis, and create charts and a PDF report to showcase the results.
• Technical Professionals: A program manager can decipher complex specifications for customer integration, instantly transforming the technical documentation into a polished, simplified guide, slide deck and a step-by-step roadmap for the team.
• Small Business Owners: A gym owner can run a media campaign and analyze raw sales data against ad spend. By calculating the campaign’s financial impact using NotebookLM, the business owner is better equipped to decide whether to expand to other cities.

These upgrades are rolling out starting today for Google AI Ultra and Workspace business customers with AI Ultra access. This will come to other tiers “over time.”