AndroidDaily - Creation and Communication: leaderboard

AndroidDaily (2026), a benchmark of everyday tasks for mobile GUI agents in real closed-source Android apps, restricted to content creation and communication tasks. Sessions are judged against task-specific guidelines; the score is the task success rate in percent; higher is better.

Metric: Task success rate (%) on content creation and communication tasks, 350 tasks in 94 real closed-source Android apps, end-to-end sessions judged by the GRADE evaluator (Gemini 3 Pro backbone, 87.37 percent agreement with human review) against three-tier task guidelines; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash61.6#175
2Gemini 3 Pro50.5#145
3Seed 1.846.5#252
4Seed 2.0 Pro44.4#222
5UI-TARS-1.543.4
6GLM-4.6V23.2#710
7Step-GUI-30A323.2
8Step-GUI-8B23.2
9UI-Venus-1.5-8B18.2
10MAI-UI-8B13.1
11GUI-Owl-1.5-8B-Think10.3
12GUI-Owl-1.5-32B-Think9.3

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=androiddaily-creation-and-communication · How It Works · Data refreshed daily, snapshot 2026-11-21.