Linch comments on What comes with cheap math?

Linch 29 Jun 2026 23:20 UTC
5 points
1
I’m a bit surprised by this, I’ve always thought that OpenAI/DeepMind models were much better at math pre-Mythos/Fable
- Mo Putera 30 Jun 2026 16:09 UTC
  7 points
  1
  Parent
  They were:
- Satya Benson 30 Jun 2026 11:02 UTC
  3 points
  0
  Parent
  I think they are (at least OAI). Notably, GPT 5.5 Pro is not on the benchmark.