---
format: "aidr-story-markdown/v1"
id: "6f66345298a07086bb7fab337e9b2e9f99e2d3bbca3cc107807f03c6275b86f0"
canonical_url: "https://aidr.today/6f663452?lang=en"
title: "Perplexity Open Sources 9B Parameter SOTA Embedding Model"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-30T19:53:35.000Z"
category: "Models"
topics: ["open-source","llm"]
source_urls: ["https://marketbrief.now/ai/perplexity-open-sources-9b-parameter-sota-embedding-model-5460e63e","https://huggingnews.com/ai/perplexity-open-sources-9b-parameter-sota-embedding-model-5460e63e","https://www.marktechpost.com/2026/09/30/perplexity-releases-pplx-embed-v2-context-9b-preview-a-contextual-embedding-model-that-retrieves-answers-and-their-supporting-evidence/","https://huggingnews.com/ai/perplexity-open-sources-decision-model-that-beats-jev-on-cost-and-perfor-d9ee89fb","https://marketbrief.now/ai/perplexity-open-sources-decision-model-that-beats-jev-on-cost-and-perfor-d9ee89fb"]
summary: "A new retrieval system outperforms the voyage-context-4 by 14.4 points in answer recall@10 during a blind evaluation on the turbopuffer private context-bench. Perplexity developed the tool, named pplx-embed-v2-context-9b-preview, to encode document chunks with the entire document in view, and the company is open sourcing the model. The 9B parameter model sets a new state of the art on ConTEB and turbopuffer benchmarks by distilling relevance from a context compression model that scores every token against a query. At 1,024 dimensions in int8, the system uses 1KB per vector and still exceeds the performance of voyage-context-4, which requires 8KB per vector."
---

# Perplexity Open Sources 9B Parameter SOTA Embedding Model

> [Open the canonical story](<https://aidr.today/6f663452?lang=en>)

**Published:** 2026-09-30T19:53:35.000Z
**Category:** Models
**Topics:** open\-source, llm

## Summary

A new retrieval system outperforms the voyage\-context\-4 by 14\.4 points in answer recall@10 during a blind evaluation on the turbopuffer private context\-bench\. Perplexity developed the tool, named pplx\-embed\-v2\-context\-9b\-preview, to encode document chunks with the entire document in view, and the company is open sourcing the model\. The 9B parameter model sets a new state of the art on ConTEB and turbopuffer benchmarks by distilling relevance from a context compression model that scores every token against a query\. At 1,024 dimensions in int8, the system uses 1KB per vector and still exceeds the performance of voyage\-context\-4, which requires 8KB per vector\.

## Sources

- [Story source](<https://marketbrief.now/ai/perplexity-open-sources-9b-parameter-sota-embedding-model-5460e63e>)
- [Story source](<https://huggingnews.com/ai/perplexity-open-sources-9b-parameter-sota-embedding-model-5460e63e>)
- [Story source](<https://www.marktechpost.com/2026/09/30/perplexity-releases-pplx-embed-v2-context-9b-preview-a-contextual-embedding-model-that-retrieves-answers-and-their-supporting-evidence/>)
- [Story source](<https://huggingnews.com/ai/perplexity-open-sources-decision-model-that-beats-jev-on-cost-and-perfor-d9ee89fb>)
- [Story source](<https://marketbrief.now/ai/perplexity-open-sources-decision-model-that-beats-jev-on-cost-and-perfor-d9ee89fb>)