Are LLMs Ready for Computer Science Education? A Cross-Domain, Cross-Lingual and Cognitive-Level Evaluation Using Professional Certification Exams

TL;DR

This study systematically evaluates four recent large language models across multiple domains, languages, and cognitive levels using certification exam questions to assess their suitability for computer science education.

Contribution

It provides a comprehensive cross-domain, cross-lingual, and cognitive-level benchmark of LLMs, highlighting their strengths and limitations for educational applications.

Findings

GPT-5 excels in English-language certifications.

Qwen-Plus performs better in Chinese contexts.

All models struggle with higher-order reasoning and complex tasks.

Abstract

Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluations aligned with formal curricula and certification standards remain limited. This study benchmarked four recent models, including GPT-5, DeepSeek-R1, Qwen-Plus, and Llama-3.3-70B-Instruct, using a dataset of 1,068 questions derived from six certification exams covering networking, office applications, and Java programming. We evaluated performance across language (Chinese vs. English), cognitive levels based on Bloom's Taxonomy, domain knowledge, confidence-accuracy alignment, and robustness to input masking. Results showed that GPT-5 performed best on English-language certifications, while Qwen-Plus performed better in Chinese contexts. DeepSeek-R1 achieved the most balanced cross-lingual performance, whereas Llama-3.3 showed clear limitations in higher-order reasoning and robustness. All models performed worse on more complex tasks. These findings provide empirical support for the integration of LLMs into computer science education and offer practical implications for curriculum design and assessment.