Google's NotebookLM gets a major update with the Gemini 3.5 model, expanded file support, and a new Antigravity feature for code execution and workflow automation.
<p>Google's NotebookLM was one of the company's first forays into generative AI technology, and in un-Googley fashion, it hasn't been shut down yet. In fact, NotebookLM is getting one of its biggest updates, ever, today, moving to the latest Gemini 3.5 model, support for more file types, and streamlined web source integration. Google also says NotebookLM will be able to do more with all those queries thanks to embedded support for Antigravity.</p>
<p>Gemini 3.5 Flash <a href="https://arstechnica.com/google/2026/05/google-announces-agent-optimized-gemini-3-5-flash-and-a-do-anything-model-called-omni/">debuted at Google I/O this year</a>, promising much faster and more efficient processing. Google has claimed that companies worried about token costs can save big by moving their projects to the new Flash model while also getting outputs that are of similar or better quality. Those improvements are now filtering down to other Google products. NotebookLM, which launched in 2023 at the very beginning of the AI boom, lets you analyze specific sources like documents and webpages with Google's latest AI models.</p>
<img width="1000" height="562" src="https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp.png" class="fullwidth full" alt="NotebookLM evaluation graph" decoding="async" loading="lazy" srcset="https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp.png 1000w, https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp-640x360.png 640w, https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp-768x432.png 768w, https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp-384x216.png 384w, https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp-980x551.png 980w" sizes="auto, (max-width: 1000px) 100vw, 1000px">
The upgraded NotebookLM beats the old version in all of Google's "core evaluation dimensions."
Credit:
Google
<p>Google conducted side-by-side evaluations of NotebookLM on the old Gemini 3.1 branch and with the updated 3.5. The company is being somewhat vague about the nature of the tests, breaking things up into "top five core evaluation dimensions," which are Accuracy and Quality, Multilingual Support, Large Document Analysis, Document Creation, and Advanced Research. In these tests, <a href="https://blog.google/innovation-and-ai/products/notebooklm/better-research-notebooklm/">Google says</a> NotebookLM averaged a 65 percent win rate versus the older model.</p><p><a href="https://arstechnica.com/ai/2026/06/gemini-3-5-and-antigravity-come-to-google-notebooklm/">Read full article</a></p>
<p><a href="https://arstechnica.com/ai/2026/06/gemini-3-5-and-antigravity-come-to-google-notebooklm/#comments">Comments</a></p>
# Gemini 3.5 and Antigravity come to Google NotebookLM
Source: [https://arstechnica.com/ai/2026/06/gemini-3-5-and-antigravity-come-to-google-notebooklm/](https://arstechnica.com/ai/2026/06/gemini-3-5-and-antigravity-come-to-google-notebooklm/)
Google’s NotebookLM was one of the company’s first forays into generative AI technology, and in un\-Googley fashion, it hasn’t been shut down yet\. In fact, NotebookLM is getting one of its biggest updates, ever, today, moving to the latest Gemini 3\.5 model, support for more file types, and streamlined web source integration\. Google also says NotebookLM will be able to do more with all those queries thanks to embedded support for Antigravity\.
Gemini 3\.5 Flash[debuted at Google I/O this year](https://arstechnica.com/google/2026/05/google-announces-agent-optimized-gemini-3-5-flash-and-a-do-anything-model-called-omni/), promising much faster and more efficient processing\. Google has claimed that companies worried about token costs can save big by moving their projects to the new Flash model while also getting outputs that are of similar or better quality\. Those improvements are now filtering down to other Google products\. NotebookLM, which launched in 2023 at the very beginning of the AI boom, lets you analyze specific sources like documents and webpages with Google’s latest AI models\.
[](https://cdn.arstechnica.net/wp-content/uploads/2026/06/IMG_NewGraph_2x.width-1000.format-webp.png)
The upgraded NotebookLM beats the old version in all of Google’s “core evaluation dimensions\.”
Credit: Google
The upgraded NotebookLM beats the old version in all of Google’s “core evaluation dimensions\.”Credit: Google
Google conducted side\-by\-side evaluations of NotebookLM on the old Gemini 3\.1 branch and with the updated 3\.5\. The company is being somewhat vague about the nature of the tests, breaking things up into “top five core evaluation dimensions,” which are Accuracy and Quality, Multilingual Support, Large Document Analysis, Document Creation, and Advanced Research\. In these tests,[Google says](https://blog.google/innovation-and-ai/products/notebooklm/better-research-notebooklm/)NotebookLM averaged a 65 percent win rate versus the older model\.
NotebookLM also now has its own “cloud computer,” which allows NotebookLM to use Antigravity to write and run code in service of your research goals\. Google says NotebookLM will come with a set of more than 100 software skills that can help you build workflows with your notebooks that previously would have required you to jump between apps\.
Google has upgraded NotebookLM with the Gemini 3.5 model, enabling more accurate responses, source discovery via Google Search, and a cloud computer for code execution and new output formats.
Google quietly enabled Gemini to ingest and reason over NotebookLM notebooks, letting users fuse private, cited documents with live web search for faster, grounded research and creative workflows.
Google Gemini has integrated NotebookLM to organize chat history, combining structured knowledge management with creative reasoning and multimodal capabilities.
Google has launched Gemini 3 Pro, a new AI model designed to outperform previous versions in coding, agentic workflows, and multimodal reasoning. The model is available via the Gemini API, Google AI Studio, and the new Google Antigravity development platform.
Google launched Antigravity 2.0, an updated agentic coding app with a new desktop app, CLI tool, SDK, and native voice support, powered by Gemini 3.5 Flash. New pricing plans were also introduced.