GE2 tops BEIR and Italian RAG benchmarks at nDCG@10 of 0.638 and 0.282 but with 231.6 ms latency; mE5-L is competitive on Italian at 31 ms while LaBSE underperforms all dedicated retrieval models.
MTEB: Massive text embedding benchmark,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems
GE2 tops BEIR and Italian RAG benchmarks at nDCG@10 of 0.638 and 0.282 but with 231.6 ms latency; mE5-L is competitive on Italian at 31 ms while LaBSE underperforms all dedicated retrieval models.