AndroidWorld

A mobile GUI agent benchmark for completing Android app workflows and on-device tasks.

  • Not in index
  • Agentic
ModelsModels with a result.9
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.N/A

Results

9 results
#ModelResultThe score from the source.
Qwen3.8 Max85.3%
Qwen3.8-27B81.9%
Qwen3.7 Plus81.0%
Holo3.1-4B71.0%
Holo3.1-9B71.0%
Qwen3.6-27B70.3%