Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
throwaway0123_5
10 days ago
|
parent
|
context
|
favorite
| on:
GPT-5
It seems like you might need less output tokens for the same quality of response though. One of their plots shows o3 needing ~14k tokens to get 69% on SWE-bench Verified, but GPT-5 needing only ~4k.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
