GPR-bench
General‑Purpose Reproducibility Benchmark
홈페이지 · 논문 1편
GPR‑bench is an open‑source, multilingual benchmark for regression testing and reproducibility tracking in generative‑AI systems. It provides a compact yet diverse suite of prompts and reference outputs that let you verify whether a model (or prompt) change alters output quality in undesirable ways.
Texts EnglishJapanese