personal finance AGI is upon us, and as this paper demonstrates, will lift all boats!
and the results of this experiment would be even stronger if ran today.
this experiment ran on GPT 5.2.
OpenAI's Personal Finance benchmark, shared around the time of 5.5, demonstrated a huge improvement over 5.3.
now we're onto 5.6, no external benchmarks to share, but I promise you it's better.
we still need to do a better job though, helping users ask better questions, so they get the best answers!
🫡 ON IT!