Ask HN: Why not compare Fable 5 with GPT "Pro"? Why compare with GPT xhigh? Every benchmark I see compares the super model Fable 5 with GPT 5.5 xhigh, but that's not a fair comparison because GPT 5.5 Pro has existed for a while and consistently delivers better results than Opus 4.8 Max, so doesn't it make more sense to compare Fable 5 with GPT Pro, instead? FYI, both of them take a long time to respond, as opposed to GPT xhigh which often returns in a couple of minutes. |
"Pro" is the tier of how much you spend each month to access tokens, while "xhigh" is the setting for how many tokens are spent on any given answer.
(Unless I've missed OpenAI having another ill-advised naming decision to confuse things again, like they did with 4o and o4 models existing at the same time).
Still, you insisting did at least let me find it: https://developers.openai.com/api/docs/models/gpt-5.5-pro
As opposed to https://developers.openai.com/api/docs/guides/reasoning#reas...