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

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

- Source: Perplexity Developers
- Published: 2026-11-02T21:51:01.000Z
- Bad Influence: https://badinfluence.news/items/ounq65bgh96v09ofid0gp1l05
- Original: https://x.com/perplexitydevs/status/2117373943896273047

## Summary

Perplexity 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. Both models also support a non-contextual mode that creates one embedding per document without chunking.

## 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.