RepoBench
Progress Over Time
Interactive timeline showing model performance evolution on RepoBench
RepoBench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Mistral AI | 22B | — | — |
What is RepoBench?
RepoBench is a benchmark for evaluating repository-level code auto-completion systems through three interconnected tasks: RepoBench-R (retrieval of relevant code snippets across files), RepoBench-C (code completion with cross-file and in-file context), and RepoBench-P (pipeline combining retrieval and prediction). Supports Python and Java programming languages and addresses the gap in evaluating real-world, multi-file programming scenarios by providing a more complete comparison of performance in auto-completion systems.
RepoBench is a text benchmark evaluating models on reasoning and code tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.3, with the leader at 0.3.
Compare leaders on the best AI for reasoning and best AI for code leaderboards.
Current leaders
Codestral-22B from Mistral AI currently leads the RepoBench leaderboard with a score of 0.340 across 1 evaluated AI models.
Source paper
- Title
- RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
- Authors
- Tianyang Liu, Canwen Xu, Julian McAuley
- Published
- arXiv
- 2306.03091
Abstract
Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment gap for more complex, real-world, multi-file programming scenarios. To fill this gap, we introduce RepoBench, a new benchmark specifically designed for evaluating repository-level code auto-completion systems. RepoBench supports both Python and Java and consists of three interconnected evaluation tasks: RepoBench-R (Retrieval), RepoBench-C (Code Completion), and RepoBench-P (Pipeline). Each task respectively measures the system's ability to retrieve the most relevant code snippets from other files as cross-file context, predict the next line of code with cross-file and in-file context, and handle complex tasks that require a combination of both retrieval and next-line prediction. RepoBench aims to facilitate a more complete comparison of performance and encouraging continuous improvement in auto-completion systems. RepoBench is publicly available at https://github.com/Leolty/repobench.
FAQ
Common questions about the RepoBench benchmark and leaderboard.