The development of large language models, such as ChatGPT, has significantly advanced in machine translation (MT), particularly in multilingual text generation and interpretation. However, assessing the translation quality of these models across diverse languages and domains remains a complex challenge. This study proposes a comprehensive approach to assessing the translation performance of ChatGPT 4o, designed to capture the nuances of its multilingual capabilities. The methodology combines traditional evaluation metrics (e.g., BLEU, METEOR, TER, ChrF, COMET, and BLEURT) with human-centered evaluation methods that prioritize linguistic quality and contextual accuracy. The evaluation spans four languages (English, Italian, French, and Croatian) and covers publicly available domain-specific texts in religion, medicine, economics, and law, comprising a total of 676 sentences. The human evaluation was conducted by two experts specializing in English-French and English-Italian language pairs, as well as 26 English language undergraduates. The assessment was based on several key criteria, including linguistic nuance, grammatical and syntactic precision, terminological consistency, contextual appropriateness, textual coherence and flow, and adherence to punctuation and formatting norms. The research addressed the following questions: Does ChatGPT provide equally accurate translations across all languages? Are there significant differences in translation quality depending on the domain? What are the most common discrepancies or errors when compared to reference translations? What is the relationship between automatic metrics and human judgments? Could ChatGPT potentially outperform a human translator in certain contexts? The analysis highlights the model’s strengths and limitations in various linguistic settings and identifies areas for improvement to enhance translation reliability.