Developed and integrated the ConvNext Base fb_in1k model into the brain-score/vision repository, expanding its model repository to support Brain-Score benchmarking for a new architecture. The work involved implementing a JSON-based region-layer mapping configuration, aligning model setup with evaluation workflows and enabling more scalable comparisons across neural architectures. Leveraging Python and skills in data science and machine learning, the integration facilitated broader coverage for brain-measure benchmarks and streamlined the evaluation pipeline. No major bugs were addressed during this period, with the primary focus on model development and cross-team collaboration to enhance the repository’s benchmarking capabilities and support future model integrations.