OpenAI’s GPT-5.4 Pro scores 150 IQ on Norway’s MENSA test, setting a new benchmark for AI reasoning and performance.
The new OpenAI GPT-5.2 model has been out for less than a week, and it’s already making top gains in deciphering the kinds of puzzles that human Mensa members have been noodling with for some time.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results