Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bouke
40 days ago
|
parent
|
context
|
favorite
| on:
Claude Opus 5
How hard can it be to be to correctly annotate the table? DeepSWE doesn’t have a highlight either; Fable slightly better than Opus (69.7% vs 68.8%).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: