← all datasets

Chinese Medical Text Embedding Benchmark (CMedTEB)

Emerging
1papers using it
2026first seen

The Chinese Medical Text Embedding Benchmark (CMedTEB) is a curated benchmark that includes tasks for retrieval, reranking, and semantic textual similarity in Chinese medical texts, designed to evaluate the performance of embedding models in medical text retrieval.

🔎 Find this dataset

Papers using Chinese Medical Text Embedding Benchmark (CMedTEB) (1)

Chinese Medical Text Embedding Benchmark (CMedTEB) — datasets — learning-to-hash