Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
grandinquistor
1 day ago
|
parent
|
context
|
favorite
| on:
Claude Opus 4.7
looking at the system card for opus 4.7 the MCRC benchmark used for long context tasks dropped significantly from 78% to 32%
I wonder what caused such a large regression in this benchmark
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I wonder what caused such a large regression in this benchmark