https://github.com/evalplus/evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

benchmark chatgpt efficiency gpt-4 large-language-models program-synthesis testing

Last synced: 12 Jan 2026

https://github.com/evalplus/repoqa

RepoQA: Evaluating Long-Context Code Understanding

Last synced: 14 Jan 2026