VenusBench-Mobile: leaderboard

Task completion of mobile GUI agents on VenusBench-Mobile (2026), user-intent Android tasks in emulated apps with screenshot observations and task-specific verification, over the 149-task primary pool. Share of tasks completed, in percent; higher is better.

Metric: Task success rate (%) on the 149-task primary pool on VenusBench-Mobile, user-intent-driven Android tasks in emulated apps (screenshot-only observations, step-by-step GUI actions, task-specific verification functions with an MLLM checker where visual or semantic judgment is needed); higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1UI-Venus-72B15.4
2MAI-UI-8B12.8
3Mobile-Agent-v3 + GUI-Owl-7B12.1
4Qwen 3 VL 30B A3B8.7#791
5UI-Venus-7B8.1
6Qwen 3 VL 8B6.7#927
7GUI-Owl-7B6.7

Interactive version: theaggregate.ai/benchmark?slug=venusbench-mobile · How It Works · Data refreshed daily, snapshot 2026-11-22.