multimodal benchmark
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.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | AC | 83.2% | 100.0% | 3 | C | |
| 02 | AC | 83.1% | 50.0% | 3 | C | |
| 03 | AC | 81.9% | 0.0% | 3 | C |
A closer view of the leading scores on this benchmark.
The leading models and scores on this benchmark.
What AITZ_EM measures and how its scores work.
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.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about AITZ_EM.
Qwen2.5 VL 72B Instruct is currently ranked first with 83.2%.
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.
Yes. Higher values rank better for this benchmark.
3 model results are currently shown.
Yes. This benchmark can contribute to the current LLMBoard capability score.