▲ | asdev 6 days ago | ||||||||||||||||
it's worse than 4.5 on nearly every benchmark. just an incremental improvement. AI is slowing down | |||||||||||||||||
▲ | usaar333 6 days ago | parent | next [-] | ||||||||||||||||
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 6 days ago | parent | prev | next [-] | ||||||||||||||||
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 6 days ago | parent | prev | next [-] | ||||||||||||||||
It's like 30x cheaper though. Probably just distilled 4.5 | |||||||||||||||||
▲ | GaggiX 6 days ago | parent | prev | next [-] | ||||||||||||||||
It's better on AIME '24, Multilingual MMLU, SWE-bench, Aider’s polyglot, MMMU, ComplexFuncBench while being much much cheaper and smaller. | |||||||||||||||||
| |||||||||||||||||
▲ | HDThoreaun 6 days ago | parent | prev | next [-] | ||||||||||||||||
Maybe progress is slowing down but after using gemini 2.5 there clearly is still a lot being made. | |||||||||||||||||
▲ | simianwords 6 days ago | parent | prev [-] | ||||||||||||||||
Sorry what is the source for this? |