Benchmark
MobilePA-Bench
A mobile AI planning capability evaluation benchmark released by Alibaba's Qwen team, designed to assess the task-planning abilities of mobile agents.
Timeline (last 90 days)
Sep 23
According to official data, Mobile Planner Agent ranks first on all three leaderboards: MobilePA-Bench, MobilePA-Bench Business, and Memory.
Expired50%
Sep 23
The benchmark suite released by the Qwen team includes MobilePA-Bench (planning), MobileWorld (cross-application execution, open-sourced on GitHub), MobileWorld-Real (real-device performance), and MobileWorld-Safety (safety evaluation).
Unverified50%