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.
Qwen2.5 VL 72B Instruct from Alibaba Cloud / Qwen Team currently leads the AITZ_EM leaderboard with a score of 0.832 across 3 evaluated AI models.
What AITZ_EM measures
AITZ_EM is a multimodal benchmark that evaluates large language models on multimodal, reasoning, and agents tasks. LLM Stats tracks 3 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 0.8.
Compare leaders on the best AI for multimodal, best AI for reasoning and best AI for agents leaderboards.
Publication
- Paper
- Android in the Zoo: Chain-of-Action-Thought for GUI Agents
- Authors
- Jiwen Zhang, Jihao Wu, Yihua Teng, Minghui Liao, and 4 others
- Published
- arXiv
- 2403.02713
Abstract
Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions should be performed and the outcomes led by the chosen action. We demonstrate that, in a zero-shot setting upon three off-the-shelf LMMs, CoAT significantly improves the action prediction compared to previous proposed context modeling. To further facilitate the research in this line, we construct a dataset Android-In-The-Zoo (AitZ), which contains 18,643 screen-action pairs together with chain-of-action-thought annotations. Experiments show that fine-tuning a 1B model (i.e. AUTO-UI-base) on our AitZ dataset achieves on-par performance with CogAgent-Chat-18B.
Qwen2.5 VL 72B Instruct leads with 83.2%, followed by Qwen2.5 VL 32B Instruct at 83.1% and Qwen2.5 VL 7B Instruct at 81.9%.
Progress Over Time
Interactive timeline showing model performance evolution on AITZ_EM
AITZ_EM Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 2 | Alibaba Cloud / Qwen Team | 34B | — | — | ||
| 3 | Alibaba Cloud / Qwen Team | 8B | — | — |
FAQ
Common questions about AITZ_EM.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions