The study evaluated the performance of large language models (LLM) on the Chinese Clinical Laboratory Qualification Examination (CCLTQE), which contains 1,600 questions focusing on four areas: clinical laboratory fundamentals, related medical knowledge, specialized knowledge, and professional competence. The researchers tested 12 different LLMs from DeepSeek, GPT, Llama, Qwen and Gemma. The best results were achieved by the Qwen3-235B model with an accuracy of 89.93%, followed by the DeepSeek-R1 model with 89.75% and QwQ-32B with 89.22%. The study demonstrated that language models optimized for the Chinese language and the specific content of laboratory medicine achieve high accuracy in this qualifying exam. The results indicate a significant potential for the use of artificial intelligence in the field of education and practice of laboratory medicine. The study thus provides empirical evidence for the application of LLM in clinical laboratory technology, an area that has been under-researched to date.