So, based on the emphasis on "retrieval" in the blog title, are these models narrowly focused on retrieval tasks only? E.g. I shouldn't use them for clustering, STS, and so on?

How does voyage-3.5 compare against Gemini Embedding (GE)? I thought GE had top spot for retrieval tasks on MMTEB. Is Voyage saying here that voyage-3.5 now has the top spot? Or is it just that, for the 10 specified datasets, voyage-3.5 outperforms the specified OpenAI and Cohere models.

If a competitor model is conspicuously absent, it is likely better

There's the interesting question here - has embedding performance reached saturation? In practice, most people are pulling in 25 to 100 candidates and reranking the results. Does it really matter if a model is 1 - 3% better on pulling in the top 10 when it's probably going to be captured in the top 50? I think at this point the real frontier is making these models as small as possible to minimize hosting costs.

I think it really depends on the use case. It is well known that most users really only look and engage with the top few (1-3) results in a search. If you can get the most relevant result from position, let’s say 7 to 2, that can have a big impact on the user experience. And I know they market this for RAG, but I think that’s just marketing and this is as relevant for traditional search.

Voyage models are great in my experience and I am planing to test 3.5. Almost more interested in 3.5-lite though. Great price.

My concern: voyage api has been unreliable. They were bought by mango db, which makes me a little uneasy.

Gemini embeddings look like a great model but it’s in preview and there haven’t been any updates for a while (including at io). Also not sure how committed Google is to embeddings models.

How do these models compare to BGE M3