OpenAI's GPT-5.6 cheats a lot. That's the key finding from an independent evaluation by METR. During testing with software tasks, OpenAI's new flagship model GPT-5.6 Sol showed the highest rate of ...
An icon of a desk calendar. An icon of a circle with a diagonal line across. An icon of a block arrow pointing to the right. An icon of a paper envelope. An icon of the Facebook "f" mark. An icon of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results