• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Report

    topk-embed-v1-small is claimed to reach frontier ranking performance on Perplexity’s private benchmark

    A member of the model’s team says the open-source, 2B model achieved that result on Q2D-Web’s combined nDCG@10 ranking metric.

    OK
    1 Source, 6h ago, first seen 6h ago

    TLDR

    A member of the team behind topk-embed-v1-small says the open-source, 2B model achieved “frontier ranking performance” on Perplexity’s private Q2D-Web benchmark, measured by combined nDCG@10. The poster thanked the team that ran the evaluation.

    Combined views

    82

    1 Source, first seen 6h ago

    Combined views

    82

    1 Source, first seen 6h ago

    4 reposts
    4 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @lateinteractionRT @marek_galovic: Our topk-embed-v1-small (2B, open-source) achieves frontier ranking performance (combined nDCG@10) on the @perplexity_ai…6h

    1 Source

    @lateinteractionRT @marek_galovic: Our topk-embed-v1-small (2B, open-source) achieves frontier ranking performance (combined nDCG@10) on the @perplexity_ai…6h