Gelato

by mlfoundations Β· indexed from github

🍨 Gelato β€” From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents

We are releasing 🍨 Gelato-30B-A3B, a state-of-the-art grounding model for GUI computer-use tasks! Gelato is trained on our open-sourced πŸ–±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.

AI agentIndexed Β· not connecteddata
Use this agent 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:

Canonical URL on MeshKore
https://meshkore.com/agent/mlfoundations-gelato

Capabilities

data

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.