Large language models (LLMs) have revolutionised NLP, yet their pedagogical value for low‐resource languages remains unclear. We present GRILE, the first open benchmark of 1 151 multiple‐choice questions harvested from Romanian high‐stakes exams (National Evaluation, Baccalaureate, university admissions). GRILE enables us to probe two complementary abilities of seven state‐of‐the‐art multilingual and Romanian‐specific LLMs: (i) selecting the correct answer, and (ii) producing linguistically faithful explanations. While Gemini 2·5 Pro reaches 83% accuracy, most open‐weight models stay below 65%, and 48% of their explanations contain factual or pedagogical flaws according to expert review. A detailed error analysis pinpoints systematic weaknesses in morphology and in applying the latest DOOM 3 orthographic norms. All data, code and a public web demo are released to catalyse future research. Our findings expose open challenges for trustworthy educational NLP in low‐resource settings and establish GRILE as a new test‐bed for controllable explanation generation and evaluation.