Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
GPT 5.4 Pro hit 38% on the hardest math benchmark: FrontierMath | Tech Twitter
Press Space to continue
GPT 5.4 Pro hit 38% on the hardest math benchmark: FrontierMath Tier 4.
It is 50 research-level math problems made by mathematicians. It can take experts weeks to solve. 99.9% of humans can even understand the problem.
A year ago, the best was 2% (o3).
Insanely impressive.
