1 Matching Annotations
  1. Last 7 days
  2. x.ai x.ai
    Introducing Grok 4.6
    1
    1. fxp007 14 Aug 2026
      It matches GPT-5.6 Sol on the Artificial Analysis Intelligence Index, which is a composite score of nine benchmarks

      Grok 4.6在综合智能指数上追平GPT-5.6 Sol——但Fable 5 Max仍领先。Benchmark的局限性在于：这些指标衡量"可测量的能力"，模型间真实差异往往在不可测的边缘场景。排名很重要，但不要过度解读。

      模型评测 AI排名 Benchmark局限
    Visit annotations in context

    Tags

    Annotators

    URL

    x.ai/news/grok-4-6