---
format: "aidr-story-markdown/v1"
id: "013513661ab5565c27295b3e21f215725cbab736ef5c10c81d1a4e8d9024994b"
canonical_url: "https://aidr.today/01351366?lang=en"
title: "Perplexity Launches 190 Million Document AI Benchmark for Agentic RAG"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-09T23:51:10.000Z"
category: "Research"
topics: ["perplexity","rag","benchmark","agent","embeddings","search"]
source_urls: ["https://huggingnews.com/ai/perplexity-launches-190-million-document-ai-benchmark-for-agentic-rag-cb818794"]
summary: "The newly released leaderboard evaluates 13 embedding models on their ability to perform large-scale web searches using agent-reformulated queries. Perplexity"
---

# Perplexity Launches 190 Million Document AI Benchmark for Agentic RAG

> [Open the canonical story](<https://aidr.today/01351366?lang=en>)

**Published:** 2026-09-09T23:51:10.000Z
**Category:** Research
**Topics:** perplexity, rag, benchmark, agent, embeddings, search

## Summary

The newly released leaderboard evaluates 13 embedding models on their ability to perform large\-scale web searches using agent\-reformulated queries\. Perplexity

## Sources

- [Story source](<https://huggingnews.com/ai/perplexity-launches-190-million-document-ai-benchmark-for-agentic-rag-cb818794>)