Noam Brown reports

Today, we at @OpenAI achieved a milestone that many considered years away: gold medal-level performance on the 2025 IMO with a general reasoning LLM—under the same time limits as humans, without tools.

Here is the link, here is some commentary.  And Nat McAleese.  And the prediction market.  Emad: “Two years ago, who would have said an IMO gold medal & topping benchmarks isn’t AGI?”  And it is good at other things too.

And from Alexander Wei: “Btw, we are releasing GPT-5 soon, and we’re excited for you to try it. But just to be clear: the IMO gold LLM is an experimental research model. We don’t plan to release anything with this level of math capability for several months.”