Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
PunchTornado
9 days ago
|
parent
|
context
|
favorite
| on:
Google's year in review: areas with research break...
What are you smoking? Gemini and Claude beat chatgpt at every metric.
aatd86
6 days ago
|
next
[–]
The metrics being the benchmarks? Perhaps but apparently these are being gamed. Which makes sense. It's the natural tendency of people.
But in my daily usage? It's a fully different story.
reply
aurareturn
9 days ago
|
prev
[–]
They don’t. GPT 5.2 and its variants are the best models right now.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
