GitHub · Python
Tencent-Hunyuan/RepoProbe
Benchmark for repository-level code understanding: 500 open-ended questions from real GitHub Discussions across 50 repositories, graded by a checklist-based verification protocol (ASE 2026)
- Stars
- 17
- Forks
- 2
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: benchmark, code-comprehension, code-understanding, dataset, evaluation, large-language-models, llm, software-engineering
Latest data point: Nov 21, 2026 · 17 stars · 2 forks