mteb/MIRACLReranking

MIRACLReranking An MTEB dataset Massive Text Embedding Benchmark MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual retrieval dataset that focuses on search across 18 different languages. Task category t2t Domains Encyclopaedic, Written Reference project-miracl.github.io You can evaluate an embedding model on this dataset using the following code: import mteb