N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
DeepSeek V4 Flash 0731: 82.7% on Terminal-Bench 2.1 with a public harness
(
antigma.ai
)
25 points by
ubermon
13 hours ago
|
5 comments
add comment
Rendered at 21:36:16 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
kimjune01 3 hours ago
[-]
an audit for the bench for the curious:
https://www.june.kim/terminal-bench-frame
ubermon 2 hours ago
[-]
yeah, that bench has a lot of room to improve, but it is the best we can find now
freakynit 13 hours ago
[-]
Keeps throwing forbidden after logging-in to the dashboard and goes back to login screen. Tried 4 times.
swrrt 9 hours ago
[-]
Oh, it seems fine for me. I can login actually. Maybe network/server instability?
freakynit 5 hours ago
[-]
No idea..
https://www.june.kim/terminal-bench-frame