Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
The cross-encoder/ms-marco-MiniLM-L6-v2 is a pre-trained Hugging Face cross-encoder model, trained on the MS MARCO Passage Ranking task for information retrieval. It encodes a query and candidate passages to produce relevance scores and ranks passages for re-ranking search results. The model can be used with SentenceTransformers or the Transformers library, with example code and benchmark performance on MS MARCO and TREC DL datasets.
Parse Score
Sources
arxiv.org shapes more of what AI says about cross-encoder/ms-marco-MiniLM-L6-v2 than any other source, at 43% of its citations.
docs.bswen.com · mongodb.com · stackai.com