Skip to content

AndroidWorld

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

8 models

Higher is better.

  1. 1Qwen3.8-Omni-FlashAlibaba87.1
  2. 2Qwen3.8 MaxAlibaba85.3
  3. 3Qwen3.8-Flash-NextAlibaba84.5
  4. 4Qwen3.8-27BAlibaba81.9
  5. 5Qwen3.7 PlusAlibaba81.0
  6. 6Holo3.1-35B-A3BH Company79.3
  7. 7Qwen3.6-27BAlibaba70.3
  8. 8Claude Opus 4.6Anthropic62.0
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Interactive mobile-agent evaluation
Tasks
Android app workflows
Authors
Z.AI (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.