AndroidDaily - Execution and Operations: leaderboard

AndroidDaily (2026), a benchmark of everyday tasks for mobile GUI agents in real closed-source Android apps, restricted to execution and operation 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 execution and operation 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 Pro64.1#146
2Gemini 3 Flash59#180
3Seed 2.0 Pro43.6#226
4Seed 1.843.6#258
5UI-TARS-1.542.3
6GLM-4.6V38.5#721
7Step-GUI-30A333.3
8Step-GUI-8B28.2
9UI-Venus-1.5-8B25.6
10GUI-Owl-1.5-32B-Think20.3
11GUI-Owl-1.5-8B-Think19.2
12MAI-UI-8B7.7

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

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