← Benchmarks
AITZ_EM
Android-In-The-Zoo (AitZ) benchmark for evaluating autonomous GUI agents on smartphones. Contains 18,643 screen-action pairs with chain-of-action-thought annotations spanning over 70 Android apps. Designed to connect perception (screen layouts and UI elements) with cognition (action decision-making) for natural language-triggered smartphone task completion.
id aitz-em · max 1 · 3 models reported
| # | Model | Score |
|---|---|---|
| 1 | Qwen2.5 VL 72B Instruct Alibaba Cloud / Qwen Team · open | 0.83 |
| 2 | Qwen2.5 VL 32B Instruct Alibaba Cloud / Qwen Team · open | 0.83 |
| 3 | Qwen2.5 VL 7B Instruct Alibaba Cloud / Qwen Team · open | 0.82 |
