Massive Text Embedding Benchmark (MTEB)

The Massive Text Embedding Benchmark (MTEB) is a dataset used to evaluate the performance of text embedding models, specifically in terms of their ability to produce meaningful and semantically relevant embeddings.

Papers using Massive Text Embedding Benchmark (MTEB) (6)

LLM2Vec-Gen: Generative Embeddings from Large Language Models2026Enhancing Lexicon-Based Text Embeddings with Large Language Models2025 · 1 citesTraining LLMs to be Better Text Embedders through Bidirectional Reconstruction2025Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning2025No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success2025Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free2024 · 1 cites