Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Introducing the Gemini 2.5 Computer Use model, an advanced agent built upon the visual reasoning strengths of Gemini 2.5 Pro, specifically crafted for direct interaction with user interfaces (UIs). This model is accessible through a newly developed computer-use tool within the Gemini API, which takes inputs such as the user's request, a screenshot of the UI context, and a log of recent actions. It adeptly generates function calls relevant to UI tasks, including clicking, typing, or selecting, while also having the capability to seek user confirmation for tasks deemed higher risk. Following each performed action, the model receives updated feedback in the form of a new screenshot and URL to facilitate a continuous process until the task is either completed or stopped. Primarily fine-tuned for web browser navigation, it also shows potential for mobile UI interactions, although it currently lacks the capability for desktop OS-level management. In various benchmarks comparing web and mobile control tasks, the Gemini 2.5 Computer Use model demonstrates superior performance over leading competitors, achieving remarkable accuracy with reduced latency, and paving the way for future enhancements in interface interaction.
Description
OmniParser serves as an advanced technique for converting user interface screenshots into structured components, which notably improves the accuracy of multimodal models like GPT-4 in executing actions that are properly aligned with specific areas of the interface. This method excels in detecting interactive icons within user interfaces and comprehending the meanings of different elements present in a screenshot, thereby linking intended actions to the appropriate screen locations. To facilitate this process, OmniParser assembles a dataset for interactable icon detection that includes 67,000 distinct screenshot images, each annotated with bounding boxes around interactable icons sourced from DOM trees. Furthermore, it utilizes a set of 7,000 pairs of icons and their descriptions to refine a captioning model tasked with extracting the functional semantics of the identified elements. Comparative assessments on various benchmarks, including SeeClick, Mind2Web, and AITW, reveal that OmniParser surpasses the performance of GPT-4V baselines, demonstrating its effectiveness even when relying solely on screenshot inputs without supplementary context. This advancement not only enhances the interaction capabilities of AI models but also paves the way for more intuitive user experiences across digital interfaces.
API Access
Has API
API Access
Has API
Integrations
Cua
GPT-4
Gemini
Gemini 2.5 Pro
Gemini 3 Deep Think
Gemini Enterprise
Gemini Enterprise Agent Platform
Google AI Studio
Integrations
Cua
GPT-4
Gemini
Gemini 2.5 Pro
Gemini 3 Deep Think
Gemini Enterprise
Gemini Enterprise Agent Platform
Google AI Studio
Pricing Details
Free
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Founded
1998
Country
United States
Website
blog.google/technology/google-deepmind/gemini-computer-use-model/
Vendor Details
Company Name
Microsoft
Founded
1975
Country
United States
Website
microsoft.github.io/OmniParser/