Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
arendtio
47 days ago
|
parent
|
context
|
favorite
| on:
Claude Opus 4.5
I think the 'Agentic coding SWE-Bench Verified' [1] was actually the one benchmark where Google didn't even claim to beat Sonnet 4.5 ;-)
[1]
https://deepmind.google/models/gemini/pro/
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
[1] https://deepmind.google/models/gemini/pro/