Long Code Arena: a Set of Benchmarks for Long-Context Code Models

TL;DR

Long Code Arena introduces six project-wide code processing benchmarks to evaluate models on tasks requiring long-context understanding, addressing a significant gap in current code processing benchmarks.

Contribution

This work provides a comprehensive suite of benchmarks, datasets, evaluation tools, and baseline solutions for long-context code processing tasks, facilitating research in this area.

Findings

Benchmark datasets for six code tasks are publicly available.

Open-source baselines demonstrate practical usage.

The benchmarks enable evaluation of models on project-wide context understanding.

Abstract

Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude over the last few years. However, there is a shortage of benchmarks for code processing that go beyond a single file of context, while the most popular ones are limited to a single method. With this work, we aim to close this gap by introducing Long Code Arena, a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions based on popular LLMs to showcase the usage of the dataset and to simplify adoption by other researchers. We publish the benchmark page on HuggingFace Spaces with the leaderboard, links to HuggingFace Hub for all the datasets, and link to the GitHub repository with baselines: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.