Gemini 3.0 AI Model Accessible Through Google AI Studio A/B Testing
By
ricklamers
Solid neighbourhood-bakery energy. Trustworthy and warm.
Summary
The article describes how the author discovered and tested Google's unreleased Gemini 3.0 AI model through A/B testing in Google AI Studio. Using SVG generation as a proxy for evaluating model quality, the author was able to access the anticipated model, which is particularly notable for expected improvements in coding performance. The testing method involved using Simon Willison's "pelican riding a bicycle" SVG generation test as an effective quality assessment tool.
Key quotes
· 3 pulledGemini 3.0 is one of the most anticipated releases in AI at the moment because of the expected advances in coding performance.
Evaluating models is a difficult task, but surprisingly the SVG generation task seems to be a very efficient proxy for gauging model quality.
Lo and behold, after trying a couple of times I got the A/B
You might also wanna read

Evaluation of Google's Gemini 3 AI Model: Performance Assessment Against Marketing Claims
The article evaluates Google's Gemini 3 AI model against the company's marketing claims, finding that while it delivers reasonably well on p

Google's Gemini 3 AI Model Tops Benchmarks and Leaderboards, Outperforming Competitors
Google's Gemini 3 AI model has been released to widespread acclaim, topping benchmarks and leaderboards while outperforming competitors like

Google Launches Gemini 3 AI Model with Enhanced Coding and Visualization Capabilities
Google is launching Gemini 3, its latest and most advanced AI model series, positioning it as the company's 'most intelligent' and 'factuall

Google's Gemini AI Now Generates Interactive 3D Models and Simulations
Google has upgraded its Gemini AI chatbot with a new feature that generates interactive 3D models and simulations in response to user questi
Google Gemini AI Adds Interactive 3D Visualizations and Simulations
Google has launched the 14th version of its Gemini AI model, which now features interactive 3D visualizations and simulations. Users can ask
Google Launches Gemini AI with Interactive 3D Visualizations and Simulations
Google has launched Gemini, its largest and most capable AI model that is multimodal and can understand and operate across text, images, aud
