MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants

TL;DR

MiniAppBench is a new benchmark for evaluating large language models' ability to generate interactive, principle-driven HTML applications, addressing a gap in existing static layout-focused assessments.

Contribution

The paper introduces MiniAppBench, a comprehensive benchmark with 500 tasks across six domains, and MiniAppEval, an agentic evaluation framework using browser automation for open-ended interaction assessment.

Findings

Current LLMs struggle with high-quality MiniApp generation.

MiniAppEval aligns well with human judgment in app evaluation.

MiniAppBench covers diverse real-world application domains.

Abstract

With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term MiniApps. These applications require models to not only render visual interfaces but also construct customized interaction logic that adheres to real-world principles. However, existing benchmarks primarily focus on algorithmic correctness or static layout reconstruction, failing to capture the capabilities required for this new paradigm. To address this gap, we introduce MiniAppBench, the first comprehensive benchmark designed to evaluate principle-driven, interactive application generation. Sourced from a real-world application with 10M+ generations, MiniAppBench distills 500 tasks across six domains (e.g., Games, Science, and Tools). Furthermore, to tackle the challenge of evaluating open-ended interactions where no single ground truth exists, we propose MiniAppEval, an agentic evaluation framework. Leveraging browser automation, it performs human-like exploratory testing to systematically assess applications across three dimensions: Intention, Static, and Dynamic. Our experiments reveal that current LLMs still face significant challenges in generating high-quality MiniApps, while MiniAppEval demonstrates high alignment with human judgment, establishing a reliable standard for future research. Our homepage is available in miniappbench.github.io.