RepoEval

RepoEval is a dataset/benchmark used to evaluate the performance of code completion models in terms of accuracy and latency.

Papers using RepoEval (8)

Balancing Latency and Accuracy of Code Completion via Local-Cloud Model Cascading2026AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion2026Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding2025Impact-driven Context Filtering For Cross-file Code Completion2025Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet'2024RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation2023 · 101 citesRepoformer: Selective Retrieval for Repository-Level Code Completion2024 · 3 citesRLCoder: Reinforcement Learning for Repository-Level Code Completion2024 · 3 cites