← Index

CONTROLAgents & automation

Jev GUI Agent Task Completion Test

Quyu Kong@kaserty
Video preview1:57
Original post ↗

This project tests Jev's ability to reliably complete tasks on mobile devices by evaluating its performance on 117 GUI-only tasks.

Jev @typesafeai gui agent demos from @trycua, @nielsmdt99 and others look insanely fast.🔥 But does that speed translate into reliable task completion on mobile-use? We tested the pair on MobileWorld’s 117 GUI-only tasks where Qwen3.8-Max plans, Jev acts (task demos below). 🧵 x.com/kaserty/status/2101309957383856577/v
Original post