mteb

Benchmark framework for evaluating text embedding models

pipmacoslinuxwindows

Try with needOr install directly

About

Massive Text Embedding Benchmark

mteb

Run evaluation on a specific embedding model with a dataset$ mteb run -m sentence-transformers/all-MiniLM-L6-v2 -t mteb/scidocs -o results/

Evaluate multiple models on multiple tasks

$ mteb run -m sentence-transformers/all-mpnet-base-v2 sentence-transformers/all-MiniLM-L6-v2 -t mteb/scidocs mteb/trec-covid

View available tasks and datasets in MTEB$ mteb show --tasks