Perplexity

@perplexity_ai

On Q2D-Web, about 70,000 production-derived search queries over 190M web documents, the 9B and 0.6B models reach 74.8% and 73.6% Recall@1000, against 69.3% for nemotron-embed-8b. https://t.co/FwltQP6jGN
打开原帖#511482
  1. Industry

    Rohan Paul: – https://arxiv.org/abs/2610.08144 Title: "Navier-Stokes lost in tran…
  2. Industry

    Rohan Paul: A new paper shows that when AI translates a math proof into Lean, pas…
  3. Industry

    Rohan Paul: Emad Mostaque: AI models "have pretty much reached the efficiency of…