正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Gemini 2.5 Pro I/O Edition is here! The best overall model just got better. I pushed it to its limits with these tests... Enjoy :)

Matthew Berman

120,728 subscribers

42,316 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

VraserX e/acc 的头像

VraserX e/acc1 年前

New Gemini 2.5 Pro literally got worse in every aspect except coding. This is a clear regression and not progress.

MatthewBerman 的头像

MatthewBerman1 年前

I saw that. Benchmarks don't tell the whole story.

CASETiFY 的头像

CASETiFY1 年前

Check out our best-selling Impact Case for #iPhone16, now with a kickstand for hands-free viewing! Get yours today. #CASETiFY

Andrew Silber - Building @ Myria 的头像

Andrew Silber - Building @ Myria1 年前

The cube test is ambiguous because to be a real “cube” it would have to have an equal number of segments per side, such as 5x5x5. Otherwise it’s just a block or prism or something. So really it should have extrapolated a 5x5x5 and included all the blocks missing from THAT.

Vincent Valentine (CEO of UnOpen.ai) 的头像

Vincent Valentine (CEO of UnOpen.ai)1 年前

amazing to see the progress and enhancements in the new model.

🐧 lalo adrian morales 𝕏 的头像

🐧 lalo adrian morales 𝕏1 年前

aside from the great video ... I love that your tests ! a little software engineer side quest!

Suhas 的头像

Suhas1 年前

Loved the video! Amazing breakdown and a little test of our own haha Now that this is here, will this take over the agentic arena as well where claude had the upper hand

BadTechBandit 的头像

BadTechBandit1 年前

Zero shot performance is great but how does it do with standard code base work in cursor or windsurf…?

MomentsOfLight 的头像

MomentsOfLight1 年前

Excellent video as usual. Thanks for the information.

相关视频

Google just launched Gemini 2.5 Pro I tested it against o1-pro with the exact same prompt

Google just launched Gemini 2.5 Pro I tested it against o1-pro with the exact same prompt

Flavio Adamo

288,802 次观看 • 1 年前

We just dropped Gemini 2.5 Pro (I/O edition). It’s our most intelligent model that’s even better at coding. Now, you can build interactive web apps in Canvas with fewer prompts. Head to and select “Canvas” in the prompt bar to try it out, and let us know what you’re building in the comments.

We just dropped Gemini 2.5 Pro (I/O edition). It’s our most intelligent model that’s even better at coding. Now, you can build interactive web apps in Canvas with fewer prompts. Head to and select “Canvas” in the prompt bar to try it out, and let us know what you’re building in the comments.

Google Gemini

470,411 次观看 • 1 年前

Very excited to share the best coding model we’ve ever built! Today we’re launching Gemini 2.5 Pro Preview 'I/O edition' with massively improved coding capabilities. Ranks no.1 on LMArena in Coding and no.1 on the WebDev Arena Leaderboard. It’s especially good at building interactive web apps - this demo shows how it can be helpful for prototyping ideas. Try it in Google Gemini, Vertex AI, and AI Studio Enjoy the pre-I/O goodies !

Very excited to share the best coding model we’ve ever built! Today we’re launching Gemini 2.5 Pro Preview 'I/O edition' with massively improved coding capabilities. Ranks no.1 on LMArena in Coding and no.1 on the WebDev Arena Leaderboard. It’s especially good at building interactive web apps - this demo shows how it can be helpful for prototyping ideas. Try it in Google Gemini, Vertex AI, and AI Studio Enjoy the pre-I/O goodies !

Demis Hassabis

996,165 次观看 • 1 年前

Google's best model is actually hidden Gemini 2.5 Pro with Web Grounding is incredible and only available in AI Studio You get free access to the most powerful model with real-time data: - Access AI Studio - Select Gemini 2.5 Pro Preview - Activate Grounding with Search Gemini will search the data, think, then give you the answers with the sources.

Google's best model is actually hidden Gemini 2.5 Pro with Web Grounding is incredible and only available in AI Studio You get free access to the most powerful model with real-time data: - Access AI Studio - Select Gemini 2.5 Pro Preview - Activate Grounding with Search Gemini will search the data, think, then give you the answers with the sources.

Paul Couvert

150,012 次观看 • 1 年前

We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In Google Gemini, here's how it transformed images of nature into code to represent unique patterns 🌱

We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In Google Gemini, here's how it transformed images of nature into code to represent unique patterns 🌱

Google DeepMind

855,311 次观看 • 1 年前

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!

elvis

81,882 次观看 • 1 年前

Gemini 2.5 Pro SwiftUI Fireworks Animation. I will share the code here:

Gemini 2.5 Pro SwiftUI Fireworks Animation. I will share the code here:

Amos Gyamfi

23,980 次观看 • 1 年前

New Gemini 2.5 Pro Preview I/O edition creates an amazing simulation of 100 men vs. a gorilla in one shot.

New Gemini 2.5 Pro Preview I/O edition creates an amazing simulation of 100 men vs. a gorilla in one shot.

Pietro Schirano

120,402 次观看 • 1 年前

"I just fell short last year. It just kind of motivated me. I got to be better. I got to be better to be with the best of the best in the league." - Juan Soto

"I just fell short last year. It just kind of motivated me. I got to be better. I got to be better to be with the best of the best in the league." - Juan Soto

SNY Mets

16,960 次观看 • 1 个月前

Gemini 2.5 Pro, our best coding model, is now available to all users! You can find it for free in the Gemini app as well as in Google AI Studio. Gemini Advanced users also now have access to it in Canvas mode. Cursor, @windsurf and Cline also added 2.5 Pro support this week!

Gemini 2.5 Pro, our best coding model, is now available to all users! You can find it for free in the Gemini app as well as in Google AI Studio. Gemini Advanced users also now have access to it in Canvas mode. Cursor, @windsurf and Cline also added 2.5 Pro support this week!

Addy Osmani

291,368 次观看 • 1 年前

Gemini 2.5 Pro is unlocking really exciting use cases at the intersection of coding and math. I remember my excitement when I first learned about the Mandelbrot set as a kid. Check out the code the Gemini 2.5 Pro model wrote given the prompt “p5js to explore a Mandelbrot set”!

Gemini 2.5 Pro is unlocking really exciting use cases at the intersection of coding and math. I remember my excitement when I first learned about the Mandelbrot set as a kid. Check out the code the Gemini 2.5 Pro model wrote given the prompt “p5js to explore a Mandelbrot set”!

Jeff Dean

18,996 次观看 • 1 年前

My most-used AI tool isn’t ChatGPT, Claude, or Gemini. It’s Sider AI Sider with Gemini 2.5 Pro. These are my top use cases and why I prefer Sider 👇 1/10 Sider AI + Gemini 2.5 Pro is my favorite way to get insights from arXiv papers.

My most-used AI tool isn’t ChatGPT, Claude, or Gemini. It’s Sider AI Sider with Gemini 2.5 Pro. These are my top use cases and why I prefer Sider 👇 1/10 Sider AI + Gemini 2.5 Pro is my favorite way to get insights from arXiv papers.

AshutoshShrivastava

36,284 次观看 • 1 年前

Gemini 3.1 Pro is the smartest model ever made. I genuinely hate using it.

Gemini 3.1 Pro is the smartest model ever made. I genuinely hate using it.

Theo - t3.gg

154,958 次观看 • 6 个月前

Before we ship a new model, these teams try to break it. They build with it, push it to its limits, and tell us where it falls short. What they find makes the final model better.

Before we ship a new model, these teams try to break it. They build with it, push it to its limits, and tell us where it falls short. What they find makes the final model better.

Claude

596,301 次观看 • 3 个月前

OG Dub VS Kai Dub The infamous "Vegeta's Pride" Speech to me I have to say I like the OG more here too the script is doing its thing with the speech, and I love it the acting in kai overall is better and yet for some reason Sabat's acting in the OG here for Vegeta is better to me he sounds evil unhinged and overall so into the performance.

OG Dub VS Kai Dub The infamous "Vegeta's Pride" Speech to me I have to say I like the OG more here too the script is doing its thing with the speech, and I love it the acting in kai overall is better and yet for some reason Sabat's acting in the OG here for Vegeta is better to me he sounds evil unhinged and overall so into the performance.

Prince Vegeta

31,372 次观看 • 1 年前

One of the early Gemini 3 tests I did was take the bouncing ball example and try to make it 10x harder, Gemini 3 Pro crush it in 1 shot... (not best of N, literally first prompt made this)

One of the early Gemini 3 tests I did was take the bouncing ball example and try to make it 10x harder, Gemini 3 Pro crush it in 1 shot... (not best of N, literally first prompt made this)

Logan Kilpatrick

305,700 次观看 • 9 个月前