This research evaluates whether large language models can effectively replace human data scientists in biomedical research contexts.

• Comprehensive benchmark for assessing LLMs on real biomedical data science tasks
• Tests across diverse data types including genomics, clinical datasets, and medical imaging
• Performance evaluation comparing advanced LLMs against human data scientists
• Practical implications for automating complex biomedical analyses

The findings address a critical gap in healthcare, where skilled data scientists are in short supply yet essential for advancing medical research and clinical applications. Understanding LLMs' capabilities could accelerate biomedical innovation while reducing resource constraints.

Can Large Language Models Replace Data Scientists in Biomedical Research?