CoREB

Cite this benchmark

@article{xue2026coreb,
  author = {Xue, Siqiao and Liao, Zihan and Qin, Jin and Zhang, Ziyin and Mu, Yixiang and Zhou, Fan and Yu, Hang},
  journal = {arXiv preprint arXiv:2605.04615},
  title = {Beyond Retrieval: A Multitask Benchmark and Model for Code Search},
  url = {https://arxiv.org/abs/2605.04615},
  year = {2026},
}

Code embedding and reranking quality across code-to-text, text-to-code, and code-to-code retrieval tasks, using counterfactually rewritten problems in five programming languages to limit training data contamination.

Reference paper →

Languages 6

Tasks 6

Task Types 2

Models 0