ADeptS-Bench (Mobile): leaderboard
ADeptS-Bench (2026) tests computer-use agents on single decision points in mobile and desktop screenshots. In the safety stream each task has a benign and a malicious variant whose interface hides a threat such as a phishing overlay or injected prompt; the score over 358 mobile task pairs is the harmonic mean of benign task success and one minus attack success, in percent; higher is better.
Metric: ADeptS-Bench score (%; harmonic mean of benign task success and one minus attack success, so capability and safety must both be high; 358 mobile task pairs across about 70 Android apps; paired benign and malicious GUI tasks with visual threats (phishing overlays, misleading buttons, prompt injection), graded on the next action against ground-truth boxes; mean of 10 runs at temperature 0.1). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 73.8 | #94 |
| 2 | Claude Opus 4.7 | 71.6 | #79 |
| 3 | GPT-5.4 | 62.7 | #123 |
| 4 | Qwen 3 VL 235B A22B | 34.7 | #479 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=adepts-bench-mobile · How It Works · Data refreshed daily, snapshot 2026-11-13.