The emerging of the AI-generated Machine Translation or Neural Machine Translation has continued the role of translator to conduct adequate post-editing for the NMT. This research is aimed to analyze the ability of English Education Department Students of University of Mataram in conducting post-editing of narrative text for Google Translate, one of widely known NMTs. The data was collected through CMC, they are the Interpreting and Translation class students’ worksheet of post-edited narrative text which previously was translated by GT. The data then were analyzed using few theories Baker’s textual equivalence theory, and harmonized metric of quality translation. Through the analyzation result, it could be inferred that most students are able to identify which sentences generated by GNMT that require post-editing and which that do not. Most of sentences left unedited by students are proven well-translated by the GNMT. Regardless, some sentences indeed still need to be post-edited after input to the GNMT, as it seems GNMT still struggles to translate well some phrases or terms that related to the culture of the language. Most students in the Translation and Interpreting class at the University of Mataram have proven their ability to identify and correct errors in GNMT-generated sentences through post-editing. This research is hoped to offer valuable insights for both education and translation and serves as a useful reference for readers seeking comprehension in this field