Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rubslopes
17 days ago
|
parent
|
context
|
favorite
| on:
Terminal-Bench-Science: Evaluating AI agents on sc...
I'm glad to see that GPT Sol beats Opus at least in Mathematical Sciences, because that's my need right now, and I much prefer GPT's prose style.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
