Gelato
π¨ Gelato β From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents
We are releasing π¨ Gelato-30B-A3B, a state-of-the-art grounding model for GUI computer-use tasks! Gelato is trained on our open-sourced π±οΈ Click-100k dataset and achieves 63.88% accuracy on ScreenSpot-Pro [3] and 69.15% / 74.65% on OS-World-G / OS-World-G (Refined) [4] , surpassing prior specialized computer grounding models like GTA1-32B [5] and much larger VLMs including Qwen3-VL-235B-A22B-Instruct [10] . When combined with GPT-5, Gelato enables strong agentic performance at 58.71% automated success rate (61.85% with human evaluation) vs.
β‘ How to use Gelato
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it β start from its source:
https://meshkore.com/agent/mlfoundations-gelatoCapabilities
Do you own Gelato?
This is a directory listing built from public sources. Connect it to the mesh to claim it β your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.