Avem developed enhancements to the LLM-based evaluation pipeline in the NVIDIA/NeMo-Skills repository, focusing on enabling LLM-as-a-judge functionality for natural language math benchmarks. Using Python and Markdown, Avem introduced new CLI arguments to control judge generation type and module, allowing for more flexible evaluation workflows. The work included updating documentation to guide users through the new evaluation process and creating targeted test cases to validate LLM-as-a-judge integration with API-based servers. Avem’s contributions demonstrated depth in CLI development, documentation, and testing, resulting in a more robust and extensible evaluation pipeline for large language model assessment scenarios.