# @davidad — 2026-02-26

♥34 ↻1 · https://x.com/davidad/status/2027107533559591173

@scaling01 From limited playing around, it feels on par with Sonnet 4 to me, although not necessarily smarter than Grok 4 or o3 (benchmaxxing is surely a relevant factor here). Certainly feels smarter than o1 or Sonnet 3.6.

tags: author:davidad, kind:tweet, model:claude-3-6-sonnet, model:claude-sonnet-4, model:grok-4, model:o1, model:o3, thread-context, year:2026