Gemini 2.5 Pro Preview: Enhanced Coding Performance – Google Developers Blog
We’ve seen developers achieving remarkable results with Gemini 2.5 Pro, so we decided to release an updated version a couple of weeks early to get it into developers’ hands sooner. Today we’re excited to launch Gemini 2.5 Pro Preview (I/O edition). This update features enhanced coding capabilities for you to start building with before Google I/O later this month. Expect significant improvements for front-end and UI development, along with enhancements in fundamental coding tasks, such as transforming and editing code, and creating sophisticated agentic workflows. “We found Gemini 2.5 Pro to be the best frontier model when it comes to ‘capability over latency’ ratio. I look forward to rolling it out on Replit Agent whenever a latency-sensitive task needs to be accomplished with a high degree of reliability.” – Michele Catasta, President, Replit
Best-in-class frontend web development
Gemini 2.5 Pro now ranks #1 on the WebDev Arena leaderboard, which measures human preference for a model’s ability to build aesthetically pleasing and functional web apps. Drawing on this leading capability, Gemini 2.5 Pro powers Cursor’s innovative code agent and strengthens our partnerships with companies like Cognition and Replit. Together, we’re pushing the frontiers of agentic programming to unlock new possibilities for developers.
“The updated Gemini 2.5 Pro achieves leading performance on our junior-dev evals. It was the first-ever model that solved one of our evals involving a larger refactor of a request routing backend. It felt like a more senior developer because it was able to make correct judgement calls and choose good abstractions.”– Silas Alberti, Founding Team, Cognition
Gemini 2.5 Pro in action
Gemini 2.5 Pro’s deep understanding of code, combined with powerful reasoning, continues to make it the go-to model for developers. We’re particularly excited about how this model can be applied in various scenarios.
Video to code
Gemini 2.5 Pro delivers state-of-the-art video understanding, scoring 84.8% on the VideoMME benchmark. Combining this with coding enables new workflows that were not possible before. For example, the Video to Learning App in Google AI Studio demonstrates how Gemini 2.5 Pro creates an interactive learning app based on a single YouTube video. With improved video understanding and complete UI, the updated Gemini 2.5 Pro model delivers a more functional experience than earlier versions.
Easier feature development
Gemini 2.5 Pro excels in front-end web development, helping you achieve more. Implementing new features traditionally required diving into design files and inspecting components to match style properties like colors, fonts, padding, margins, and borders, and then manually writing the CSS code needed. Now, imagine using Gemini 2.5 Pro in an IDE and having the model generate new features, like adding a video player styled consistently with other apps in the Gemini 95 starter app.
Quick concepts to working apps
Bringing ideas to life with both functionality and a beautiful UI is easier with Gemini 2.5 Pro. The new dictation starter app, built using this updated model, exemplifies this. Notice details like the wavelength animations, responsive design, and subtle button hover effects. By default, the model has a strong sense of aesthetic web development while maintaining steerability, helping developers swiftly transform a concept into a functional web app. Gemini 2.5 Pro was able to design and code the microphone UI animation for the dictation starter app.
Start building with Gemini 2.5 Pro
You can utilize Gemini 2.5 Pro with the Gemini API in Google AI Studio, and enterprise customers can access it via Vertex AI. For developers already using Gemini 2.5 Pro, this new version will not only enhance coding performance but also address key developer feedback, such as reducing errors in function calling and improving function calling trigger rates. The previous iteration (03-25) now points to the most recent version (05-06), so no action is required to use the improved model, and it remains available at the same price. We have also updated the model card with the new version of 2.5 Pro. We can’t wait to see the incredible apps you create!
