Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation

TL;DR

Decompile-Bench is a large-scale, open-source dataset of two million binary-source function pairs designed to advance the development and evaluation of LLM-based binary decompilers, addressing previous limitations in benchmark quality and scale.

Contribution

It introduces the first extensive binary-source function pair dataset and a comprehensive evaluation benchmark for LLM decompilation, improving assessment accuracy and model training.

Findings

Fine-tuning with Decompile-Bench improves re-executability by 20%.

The dataset covers 2 million function pairs from 100 million binaries.

Evaluation metrics are thoroughly analyzed for decompiler assessment.

Abstract

Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchmark that provides large-scale binary-source function pairs, which is critical for advancing the LLM decompilation technology. Creating accurate binary-source mappings incurs severe issues caused by complex compilation settings and widespread function inlining that obscure the correspondence between binaries and their original source code. Previous efforts have either relied on used contest-style benchmarks, synthetic binary-source mappings that diverge significantly from the mappings in real world, or partially matched binaries with only code lines or variable names, compromising the effectiveness of analyzing the binary functionality. To alleviate these issues, we introduce Decompile-Bench, the first open-source dataset comprising two million binary-source function pairs condensed from 100 million collected function pairs, i.e., 450GB of binaries compiled from permissively licensed GitHub projects. For the evaluation purposes, we also developed a benchmark Decompile-Bench-Eval including manually crafted binaries from the well-established HumanEval and MBPP, alongside the compiled GitHub repositories released after 2025 to mitigate data leakage issues. We further explore commonly-used evaluation metrics to provide a thorough assessment of the studied LLM decompilers and find that fine-tuning with Decompile-Bench causes a 20% improvement over previous benchmarks in terms of the re-executability rate. Our code and data has been released in HuggingFace and Github. https://github.com/albertan017/LLM4Decompile