Even if you consider IQ a useful measure in general, it is adjusted for age and gender and to match distribution in population. It doesn't really make sense to assign IQ to LLMs.
OpenAI O3 is 117 IQ on June 2nd.
Bing copilot is 67 IQ.
It is being tested weekly; along all the others as well.
Personally it's not a useful measurement.
Even if you consider IQ a useful measure in general, it is adjusted for age and gender and to match distribution in population. It doesn't really make sense to assign IQ to LLMs.