News for hackers. Stuff that matters.
Re:GPT-4.1 in the API by asdev on Monday April 14, 2025 @01:30PM (#43683829)
it's worse than 4.5 on nearly every benchmark. just an incremental improvement. AI is slowing down
Re:GPT-4.1 in the API by Nckpz on Monday April 14, 2025 @01:59PM (#43684227)
They don't disclose parameter counts so it's hard to say exactly how far apart they are in terms of size, but based on the pricing it seems like a pretty wild comparison, with one being an attempt at an ultra-massive SOTA model and one being a model scaled down for efficiency and probably distilled from the big one. The way they're presented as version numbers is business nonsense which obscures a lot about what's going on.
Re:GPT-4.1 in the API by usaar333 on Monday April 14, 2025 @02:24PM (#43684506)
Or OpenAI is? After using Gemini 2.5, I did not feel "AI is slowing down". It's just this model isn't SOTA.
Re:GPT-4.1 in the API by conradkay on Monday April 14, 2025 @01:39PM (#43683959)
It's like 30x cheaper though. Probably just distilled 4.5
Re:GPT-4.1 in the API by HDThoreaun on Monday April 14, 2025 @03:29PM (#43685246)
Maybe progress is slowing down but after using gemini 2.5 there clearly is still a lot being made.
Re:GPT-4.1 in the API by simianwords on Monday April 14, 2025 @01:58PM (#43684214)
Sorry what is the source for this?
Re:GPT-4.1 in the API by GaggiX on Monday April 14, 2025 @01:52PM (#43684136)
It's better on AIME '24, Multilingual MMLU, SWE-bench, Aider’s polyglot, MMMU, ComplexFuncBench while being much much cheaper and smaller.
Re:GPT-4.1 in the API by asdev on Monday April 14, 2025 @01:56PM (#43684195)
and it's worse on just as many benchmarks by a significant amount. as a consumer I don't care about cheapness, I want the maximum accuracy and performance
Re:GPT-4.1 in the API by GaggiX on Monday April 14, 2025 @02:57PM (#43684814)
As a consumer you care about speed tho, and GPT-4.5 is extremely slow, at this point just use a reasoning model if you want the best of the best.