IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks

TL;DR

IDE-Bench is a comprehensive framework for evaluating AI-powered IDE agents on real-world software engineering tasks across multiple languages and stacks, using a structured, IDE-native interface.

Contribution

It introduces a Dockerized test harness with high-level abstractions for code search, editing, and testing, enabling systematic evaluation of AI IDE agents in realistic scenarios.

Findings

First benchmark to correlate agent intent with project success in multi-language environments.

Evaluates agents on tasks like feature development, bug fixing, and refactoring.

Provides a public leaderboard for ongoing benchmarking.

Abstract

IDE-Bench is a comprehensive framework for evaluating AI IDE agents on real-world software engineering tasks through an IDE-native tool interface. We present a Dockerized test harness that goes beyond raw terminal execution, granting models a structured tool ecosystem that represents AI-native IDEs like Cursor and Windsurf. By providing high-level abstractions for codebase search, structured file editing, and tools for testing full-stack applications, IDE-Bench evaluates an agent's ability to act as a true engineering collaborator. For evaluation and to prevent training data contamination, we created 80 tasks across eight never-published repositories spanning C/C++, Java, and MERN stacks, representing modern tech stack production scenarios, including feature implementation, bug fixing, refactoring, and performance optimization that mirror daily developer workflows in private codebases. Our benchmark is the first to systematically correlate agent-reported intent with successful project-level modifications in a multi-language, full-stack environment on completely uncontaminated code. We release IDE-Bench and a public leaderboard at: https://ide-bench.com.