• SSUPII@sopuli.xyz
    link
    fedilink
    English
    arrow-up
    1
    ·
    2 months ago

    Benchmarks mean nothing to general usage. And Google models have historically been extremely poor at that.

    • drawerair@lemmy.worldOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      2 months ago

      Gpt high was better than Gemini pro for me in the previous months. 🕑 will tell if Gemini 3 deep think is great.