chatgpt vs. google translate: comparative analysis of translation quality

The rise of large language models and their use in machine translation has prompted the need to examine the quality of their translations and compare them with other systems. this study aimed to assess the quality of literary translation from persian to english using chatgpt and google translate. a persian short story was chosen, and both tools were used to generate translations. the translations were evaluated using sofyan and tarigan's (2019) functional holistic model, resulting in scores of 56% and 40% respectively. additionally, a critical error analysis was conducted to identify areas where the tools struggled with effective translation, highlighting their strengths and weaknesses. these scores indicate that both machine translation systems have limitations in terms of accuracy, equivalence, and text function, particularly in literary translation. moreover, the findings of this study emphasize the importance of human translators in achieving high-quality translations that effectively convey cultural nuances and idiomatic expressions in persian to english literary translations, despite the convenience offered by machine translation systems for quick translations.