Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
A New Chess Benchmark for Language Models
(
chessbench.ai
)
2 points
by
soltanov
1 day ago
|
past
|
discuss
Gemini 3.8 Flash passed Claude Fable 5.1 on this bench
(
chessbench.ai
)
2 points
by
soltanov
1 day ago
|
past
|
discuss
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
