Worked on expanding multilingual benchmarking capabilities in the embeddings-benchmark/mteb repository by adding support for Chinese language embeddings. Developed new model definitions and a custom wrapper to integrate Sentence Transformers, enabling direct evaluation of Chinese embeddings within the MTEB framework. This involved Python-based model integration and careful registration of new models to ensure seamless adoption by teams working with Chinese NLP models. The work broadened the language coverage of MTEB, allowing for more comprehensive benchmarking and data-driven evaluation of Chinese language models. Focus was placed on maintainable code quality and facilitating research and product decisions through improved benchmarking infrastructure.