The Gemini team cooked hard with Gemini 2.5 Pro, it's an awesome model that continues to lead lmarena.ai - huge congrats to the team! Try it for yourself in the Google Gemini App now. Can't wait for you all to see what else we've been cooking 👀

Recently had the pleasure of lecturing back at Princeton in a grad seminar. I took the opportunity to cover how scaling laws have evolved since their inception, leaning heavily on great external content from my colleagues Sebastian Borgeaud JB Alayrac Jacob Austin . Content in thread

although the vision leaderboard doesn't capture every vision use case, 60+ elo points reflects the significant step in core vision capabilities like transcription, spatial understanding, reading charts/diagrams & many more. Still a lot more to do, but 2.5 Pro is the best vision

Worth reading this. The video understanding capabilities of Gemini are fantastic.

Gemini 2.5 Pro is incredible at video understanding, try posting a YouTube link into AI studio ai.dev and asking it questions about the video. You will be amazed!

A lot of work went to make Gemini 2.5 SOTA at video understanding, check out this 🧵 for more details! Looking back at where we were a year ago, the progress really feels phenomenal! So many things to unlock and enable from video 🎥 and we are only getting started!

Gemini 2.5 Pro sets the state of the art on our newly released Minerva video reasoning benchmark by scoring 63.5%. 📜 Paper: arxiv.org/abs/2505.00681… 📊 Dataset: github.com/google-deepmin…

The Gemini 2.5 models are magical for analyzing sports video. We asked Gemini to find Draymond's defensive plays from a highlights reel, which requires the model to: - reason “over pixels” to identify defensive plays - identify players in the video using its world knowledge -

cooking up something tasty for tomorrow...

Excited that our work on Gemini Robotics and Gemini spatial understanding have just been featured on #GoogleIO stage! I believe that a frontier model possessing strong real-world understanding capabilities represents the ultimate path to embodied AGI, and we are making rapid

People want Veo 3 so we are giving access to Pro subscribers in 71 countries as of...now!

By popular request, you can now specify frames per second (fps), as well as start and end times, for videos in AI Studio ⏩

Many Congratulations to Jianyuan#CVPR2025 2025, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht and David Novotny for winning the Best Paper Award @CVPR for "VGGT: Visual Geometry Grounded Transformer" 🥇🎉 🙌🙌 #CVPR2025!!!!!!

Pre-training is not dead

The newly generally available Gemini 2.5 Flash and Pro are even better at video understanding than the versions we shared in the blog a month ago, see more details in the tech report 😀

You can now sample at higher frame rates (default 1 FPS), and specify start and end times for videos in the Gemini API! We’ve been blown away by all the ways developers are using Gemini to process videos, and see a ton of devs manually clipping and slowing down videos to use

We just shipped video FPS support in the Gemini API, so you can dynamically customize how many frames per second you want the model to see, unlocking lots of interesting new video use cases! 📹

gemini's still the only frontier model that supports native video input (and is amazing at it!) incredible amount of real-world utility given how much of the world's information is increasingly in video