AndroidDaily - Information and Decision: leaderboard

AndroidDaily (2026), a benchmark of everyday tasks for mobile GUI agents in real closed-source Android apps, restricted to information-seeking and decision 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 information-seeking and decision 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 Flash63.6#175
2Gemini 3 Pro60.7#145
3Seed 1.847.4#252
4Seed 2.0 Pro46.8#222
5UI-TARS-1.541.6
6GLM-4.6V36.4#710
7Step-GUI-8B32.9
8Step-GUI-30A331.8
9GUI-Owl-1.5-32B-Think29.7
10UI-Venus-1.5-8B24.4
11GUI-Owl-1.5-8B-Think23.7
12MAI-UI-8B8.7

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

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