MTEB
Benchmark suite ranking embedding models across many tasks.
Resumen
MTEB evaluates embedding models across a wide set of tasks - retrieval, clustering, classification, reranking - in several languages, and publishes a single ranking. It solves the problem that "which embedding model" is otherwise answered by vendor claims on cherry-picked tasks. It exists because retrieval quality is decided at the embedding step, so a comparable ranking across models is the most useful single number in a RAG stack.
Grafo de tecnologías
Cómo se conecta MTEB con el resto del stack.
Usa y depende de
- BEIR benchmark Benchmarks MTEB based on BEIR High ✓ source
Aplicado a
- Embedding concept Techniques MTEB used for Embedding High ✓ source
Herramientas
Software que implementa o se integra con MTEB.