Ryan Haines / Android Authority
TL;DR
- Google app beta users on Android can now choose between different Gemini models.
- The latest Gemini 2.0 Flash model is also available for testing on Android.
- This feature gives users more control over their AI experience on their smartphones.
Google Gemini is shaping up to be a great AI assistant, especially when you see how little others have progressed. While ChatGPT has an edge in a few areas, Gemini’s deeper integration within Android flagships and tie-in with Google Search makes it almost second nature. Google recently announced the new Gemini 2.0 Flash model, which is said to outperform 1.5 Pro on key benchmarks. You can try this out on the web, but if you want to try it on your phone, you can now do so with the latest Google app beta.
Google app v15.49.42 beta adds support for choosing a specific Gemini version for your queries. This setting was already available on the web for Gemini Advanced users with the announcement of Gemini 2.0 Flash last week, and the feature is now making its way to the Android app. Users will be able to change the Gemini model by clicking on the header area where the current model name is shown.
Users will be able to choose from the following models, with each having its own set of pros and cons:
- Gemini 1.5 Pro: For complex tasks
- Gemini 1.5 Flash: For everyday tasks where execution speed is equally important.
- Gemini 2.0 Flash Experimental: Gemini’s latest model is available for testing.
When we activated the feature ahead of its rollout in this app version, we couldn’t select the 2.0 Flash Experimental version.
With Google app v15.50.37 beta, the feature is now rolling out in the beta branch. Users can also use the Gemini 2.0 Flash experimental model.
It may feel like selecting the latest model would be the best fit, but there’s a reason why it is labeled “Experimental.” Certain features might not work as expected, and some are not even available. So, for now, you’d be better off choosing 1.5 Flash for everyday queries and 1.5 Pro for deeper research tasks.
Users in the stable branch will have to wait a little, but given how important this is for Google, we reckon this will be available for users sooner rather than later.