why would xhigh -> max increase the cost but lowers the score on frontier 2.0 bench?
Just a hunch but I think there's a signal to noise ratio issue that starts to pollute things when the reasoning content starts to massively outsize the original ask.
alt Hacker News
Just a hunch but I think there's a signal to noise ratio issue that starts to pollute things when the reasoning content starts to massively outsize the original ask.