Skip to content
View original post on X: Perplexity DevelopersOfficial
Published
31/100

Perplexity's embedding models rank top on ViDoRe-V3 markdown retrieval

AIPerplexity says its 0.6B embedding model is the strongest sub-1B model on ViDoRe-V3 markdown, whether chunked or unchunked. Its contextual 9B model with 128-token chunks ranks second only to voyage-context-4.
Perplexity DevelopersVerified on XOfficial
@perplexitydevs
View on X

Part of a thread · earlier post

Both models also run in non-contextual mode: one embedding per document, no chunking.

On ViDoRe-V3 markdown, the 0.6B is the strongest sub-1B model, chunked (contextual) or unchunked (non-contextual). The contextual 9B with 128-token chunks is second only to voyage-context-4.

Source details

Perplexity Developers · x.comPublished · added here

Original title: Both models also run in non-contextual mode: one embedding per document, no chunking.

Topics

Open-source ecosystemPapers & researchEvals & benchmarks