GeneBench-Pro is a benchmark that evaluates the performance of AI models in genomics and precision medicine. It includes 10 case studies with representative questions, datasets, and supporting materials. The case studies cover various topics, such as estimating the clinical utility of a synthetic inhibitor, deciding whether an apparent lncRNA dependency is transcript-specific, and estimating direct disease effects for nearby proteins. The benchmark provides a comprehensive evaluation of AI models in genomics and precision medicine, which is significant because it can help improve the accuracy and reliability of AI-driven medical decisions, and why it matters is that it has the potential to revolutionize personalized medicine by enabling more precise and effective treatments.