top | item 43197280

(no title)

anothermathbozo | 1 year ago

Looks like o1 performance without reasoning. Pretty good but seems reasonable that they didn’t want to call this 5 as they’ve already got a product out there that is as performant.

Another notable thing here is a big drop in hallucination rate as measured by their benchmarks (for whatever those are worth).

discuss

order

YetAnotherNick|1 year ago

Which graph are you looking at? It's not even close to o1. I think the bigger point here is efficiency not the performance. If we could get it in Gemini flash level pricing or twice of that it would be revolutionary otherwise it would be meh at best.

EDIT: Its 30 times more expensive than 4o lol