Meta’s vanilla Maverick AI model ranks below rivals on a popular chat benchmark

  • staffstaff
  • AI
  • April 11, 2025
  • 0 Comments

Earlier this week, Meta landed in hot water for using an experimental, unreleased version of its Llama 4 Maverick model to achieve a high score on a crowdsourced benchmark, LM Arena. The incident prompted the maintainers of LM Arena to apologize, change their policies, and score the unmodified, vanilla Maverick. Turns out, it’s not very […]

  • Related Posts

    Early cancer detection startup Craif raises $22M

    Cancer ranks as one of the top causes of death worldwide. The National Cancer Institute reported nearly 20 million new cancer cases and 9.7 million cancer-related deaths globally in 2022,…

    Continue reading
    Welcome to Chat Haus, the coworking space for AI chatbots

    Nestled between an elementary school and a public library in Brooklyn’s Greenpoint neighborhood sits a new kind of “luxury” coworking space.  Dubbed the Chat Haus, this space has many of…

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    Early cancer detection startup Craif raises $22M

    • By staff
    • April 28, 2025
    • 1 views

    Welcome to Chat Haus, the coworking space for AI chatbots

    • By staff
    • April 27, 2025
    • 1 views

    Report finds Meta’s celebrity-voiced chatbots could discuss sex with minors

    • By staff
    • April 27, 2025
    • 2 views

    Google’s DeepMind UK team reportedly seeks to unionize

    • By staff
    • April 26, 2025
    • 2 views