If they didn’t constantly reset, they’d be about the same as Anthropic.
Right now, I find that Grok offers better value, uses fewer tokens per turn, and makes better code. I haven’t tried Cursor because I don’t want to change editors again, but maybe I should try it…
That is not true; GPT is the most reasoning efficient model family on the market.
Are there any projects that track how much usage of each model translates to how much percentage drop in weekly/5hr windows?