Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
OpenAI's GPT-OSS models benchmarks worse than DeepSeek R1 and Qwen3 235B
(
xcancel.com
)
8 points
by
pu_pe
4 months ago
|
hide
|
past
|
favorite
|
1 comment
davely
4 months ago
[–]
Not entirely unexpected given that these models have 2x - 5x more parameters than the 120b gpt-oss model.
It’s impressive their performance gets so close given the size!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
It’s impressive their performance gets so close given the size!