undefined | Better HN

0 pointsoof-baroomf7mo ago0 comments

74.9 SWEBench. This increases the SOTA by a whole .4%. Although the pricing is great, it doesn't seem like OpenAI found a giant breakthrough yet like o1 or Claude 3.5 Sonnet

0 comments

Workaccount27mo ago

I'm pretty sure 3.5 sonnet always benchmarked poorly, despite it being the clear programming winner of it's time.

iLoveOncall7mo ago

That would assume there is a giant breakthrough to be found.

j / k navigate · click thread line to collapse

0 pointsoof-baroomf7mo ago0 comments

74.9 SWEBench. This increases the SOTA by a whole .4%. Although the pricing is great, it doesn't seem like OpenAI found a giant breakthrough yet like o1 or Claude 3.5 Sonnet

0 comments

Workaccount27mo ago

I'm pretty sure 3.5 sonnet always benchmarked poorly, despite it being the clear programming winner of it's time.

iLoveOncall7mo ago

That would assume there is a giant breakthrough to be found.

j / k navigate · click thread line to collapse