MobileWorld
A mobile-use agent benchmark for completing interactive tasks in smartphone environments.
1 models
Higher is better.
- 1Qwen3.8 MaxAlibaba77.8
About this benchmark
- Metric
- Mobile agent task score
- Tasks
- Interactive mobile-device workflows
- Authors
- Qwen Team (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.