asdev 5 days ago

it's worse than 4.5 on nearly every benchmark. just an incremental improvement. AI is slowing down

6
usaar333 5 days ago

Or OpenAI is? After using Gemini 2.5, I did not feel "AI is slowing down". It's just this model isn't SOTA.

Nckpz 5 days ago

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.

conradkay 5 days ago

It's like 30x cheaper though. Probably just distilled 4.5

GaggiX 5 days ago

It's better on AIME '24, Multilingual MMLU, SWE-bench, Aider’s polyglot, MMMU, ComplexFuncBench while being much much cheaper and smaller.

asdev 5 days ago

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

GaggiX 5 days ago

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.

HDThoreaun 5 days ago

Maybe progress is slowing down but after using gemini 2.5 there clearly is still a lot being made.

simianwords 5 days ago

Sorry what is the source for this?