Comparative evaluation of ChatGPT and DeepSeek across key NLP tasks: Strengths, weaknesses, and domain-specific performance
Wael Etaiwi, Bushra Alhijawi
Abstract
The increasing use of large language models (LLMs) in natural language processing (NLP) tasks has sparked significant interest in evaluating their effectiveness across diverse applications. While models like ChatGPT and DeepSeek have shown strong results in many NLP domains, a comprehensive evaluation is needed to understand their strengths, weaknesses, and domain-specific abilities. This is critical as these models are applied to various tasks, from sentiment analysis to more nuanced tasks like textual entailment and translation. This study aims to evaluate ChatGPT and DeepSeek across five key NLP tasks: sentiment analysis, topic classification, text summarization, machine translation, and textual entailment. A structured experimental protocol is used to ensure fairness and minimize variability. Both models are tested with identical, simple prompts and evaluated on two benchmark datasets per task, covering domains like news, reviews, and formal/informal texts. The results demonstrate that DeepSeek outperforms ChatGPT by 6.73% in accuracy on classification tasks, showcasing its strength in classification stability and logical reasoning. Meanwhile, ChatGPT shows a modest 0.33% improvement in BERTScore on generation tasks, reflecting its nuanced understanding and flexibility advantage. These findings offer valuable guidance for selecting the most suitable LLM depending on whether a task prioritizes classification accuracy or generative quality.