Benchmark

AndroidWorld

Measures: An agent operates a live Android emulator across 20 apps to complete 116 parameterised tasks (randomised each run), checked from device state; scored as % of tasks completed.

Maintainer
Google Research / Google DeepMind
Introduced
2024
Status
Active
Saturation
Saturated
Typical provenance
Mixed
In scoring set
No

PaperOfficial leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.