News for hackers. Stuff that matters.

A comment on Open models by OpenAI. Parent comment

Re:Open models by OpenAI by modeless on Tuesday August 05, 2025 @03:46PM (#44803320)
> Both of them are comparable to OpenAI's largest models and even bench favorably to Deepseek and Opus

So are/do the new OpenAI models, except they're much smaller.

[ Parent | on HN ]
Re:Open models by OpenAI by UrineSqueegee on Tuesday August 05, 2025 @04:12PM (#44803633)
I'd really wait for additional neutral benchmarks, I asked the 20b model on low reasoning effort which number is larger 9.9 or 9.11 and it got it wrong.

Qwen-0.6b gets it right.

[ Parent | on HN ]
Re:Open models by OpenAI by bigyabai on Tuesday August 05, 2025 @06:36PM (#44805352)
According to the early benchmarks, it's looking like you're just flat-out wrong: https://blog.brokk.ai/a-first-look-at-gpt-oss-120bs-coding-a...
[ Parent | on HN ]