Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks

TL;DR

Web-Bench is a new, comprehensive benchmark for evaluating large language models in web development tasks, emphasizing real-world workflows and foundational web standards and frameworks.

Contribution

The paper introduces Web-Bench, a challenging, multi-project benchmark based on real-world web development tasks, addressing saturation issues in existing LLM code benchmarks.

Findings

SOTA LLM achieves only 25.1% Pass@1 on Web-Bench.

Web-Bench projects are designed by experienced engineers, increasing difficulty.

Benchmark highlights the need for LLM optimization for web standards and frameworks.

Abstract

The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM code benchmarks primarily focused on code generation accuracy, but these benchmarks have gradually become saturated. Benchmark saturation weakens their guiding role for LLMs. For example, HumanEval Pass@1 has reached 99.4% and MBPP 94.2%. Among various attempts to address benchmark saturation, approaches based on software engineering have stood out, but the saturation of existing software engineering benchmarks is rapidly increasing. To address this, we propose a new benchmark, Web-Bench, which contains 50 projects, each consisting of 20 tasks with sequential dependencies. The tasks implement project features in sequence, simulating real-world human development workflows. When designing Web-Bench, we aim to cover the foundational elements of Web development: Web Standards and Web Frameworks. Given the scale and complexity of these projects, which were designed by engineers with 5 to 10 years of experience, each presents a significant challenge. On average, a single project takes 4 to 8 hours for a senior engineer to complete. On our given benchmark agent (Web-Agent), SOTA (Claude 3.7 Sonnet) achieves only 25.1% Pass@1, significantly lower (better) than SWE-Bench's Verified (65.4%) and Full (33.8%) scores. Finally, we discuss that in any development field, Standards and Frameworks represent foundational knowledge and efficiency tools, respectively, and LLMs require optimization tailored to them.