Cua AI releases Cua-Bench-S1 benchmark and Cua-S1-Nano/4B computer-use models

ycombinator · x · 2026-09-22

Cua AI introduced Cua-Bench-S1, a benchmark for evaluating decision models built for computer use, including its new model Jev.

Alongside it, the team released the first generation of Cua-S1 models with two checkpoints:

Weights are up on Hugging Face with an open-source repo, ready for developers building computer-use agents.

Original post →

More from coding & agent

coding & agent channel →