It seems that pass rate decreases with effort increase, on GPT5.5? This is highly counter-intuitive and I don't see any explanation, any idea why they'd get this result?
It seems that pass rate decreases with effort increase, on GPT5.5? This is highly counter-intuitive and I don't see any explanation, any idea why they'd get this result?
Looks to be within the realm of natural variance expected from naturally variable models, ie error bars.