ResearchSep 10, 2026 · 06:514 sources

Perplexity Launches 190 Million Document AI Benchmark for Agentic RAG

From huggingnews.com

Image: huggingnews.com
AI;DR

Perplexity has launched a 190 million document AI benchmark for agentic RAG, with a leaderboard evaluating 13 embedding models on large-scale web searches using agent-reformulated queries.

Read the sourceSign in to suggest

Sources

+ 3 more
  1. SUPPORT@perplexity_ai“190M web documents, 69,721 agent-reformulated queries, and 99.6 positive judgments per query”x.com
  2. SUPPORT@perplexity_ai“reduces evaluation from 4,608 to roughly 1,500 H200 GPU-hours”x.com
  3. SUPPORT@perplexity_ai“pplx-embed-v1-4b leads Web Ranking (65.73) and Combined (69.11)”x.com
#perplexity#rag#benchmark#agent#embeddings#searchMarkdown
Content history (1)
  • 2026-10-04 · Summary · vi · Wording fix
    Perplexity vừa ra mắt một bộ chuẩn đánh giá AI mới dựa trên 190 triệu tài liệu, thiết kế …
    Perplexity vừa ra mắt một bộ chuẩn đánh giá AI mới dựa trên 190 triệu tài liệu, thiết kế …

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today