Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

GPQA Diamond: gpt-oss-120b: 80.1%, Qwen3-235B-A22B-Thinking-2507: 81.1%

Humanity’s Last Exam: gpt-oss-120b (tools): 19.0%, gpt-oss-120b (no tools): 14.9%, Qwen3-235B-A22B-Thinking-2507: 18.2%



Wow - I will give it a try then. I'm cynical about OpenAI minmaxing benchmarks, but still trying to be optimistic as this in 8bit is such a nice fit for apple silicon


Even better, it's 4 bit


Glm 4.5 seems on par as well


GLM-4.5 seems to outperform it on TauBench, too. And it's suspicious OAI is not sharing numbers for quite a few useful benchmarks (nothing related to coding, for example).

One positive thing I see is the number of parameters and size --- it will provide more economical inference than current open source SOTA.


Was the Qwen model using tools for Humanity's Last Exam?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: