cross-posted from: https://lemmy.world/post/39002420

Gemini 3 deep think seems ๐Ÿ‘. I'll try it. My 2nd pick is Gpt 5.1 high. My 3rd pick is Claude sonnet 4.5 โ€“ thinking. The llm race is still ๐Ÿ”ฅ.

you are viewing a single comment's thread
view the rest of the comments
[โ€“] 1 point 11 months ago (1 child)

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

  • source
  • hideshow 1 child comment