The page doesn't load for me, but surely token consumption isn't a very good metric?
A poor model could require many more runs to solve a task, or much longer internal 'thinking' runs - all of which will increase token consumption but are a bad thing for the user.
A poor model could require many more runs to solve a task, or much longer internal 'thinking' runs - all of which will increase token consumption but are a bad thing for the user.