its not the language that communicated its the people. You recruit mediocres in different languages they all communicated in the same mid , 39 bits or whatever. Let two geniuses have a chat or even two teenagers - its a different ball game than 39 bits
i have asked the direction of friction on ball rolling either up or down on an inclined plan - it gave wrong answer and was adamant about it. Surprisingly, similar to o1.
gave a problem which sounds like monty hall problem but a simple probability question and it nailed it.
asked to tell a joke - horrible joke ever.
much better than o1 but still no where near agi. it has been optimized for logic and reasoning at best.