News for hackers. Stuff that matters.

A comment on Not Even Bronze: Evaluating LLMs on 2025 International Math Olympiad. Parent comment

Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by kenjackson on Saturday July 19, 2025 @10:52AM (#44615950)
OpenAI achieved Gold on an unreleased model. GPT-5. Read the tweets and they explain what they did.
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by e1g on Saturday July 19, 2025 @11:06AM (#44616089)
OpenAI explicitly said it’s not GPT-5 but another experimental research model https://x.com/alexwei_/status/1946477756738629827?s=46
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by kenjackson on Saturday July 19, 2025 @11:18AM (#44616224)
Thanks. I parsed that wrong. In either case not the same thing Math Arena used.
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by idiotsecant on Saturday July 19, 2025 @11:00AM (#44616016)
Actually, I did it a year ago but I just don't want to release my model.
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by senkora on Saturday July 19, 2025 @11:03AM (#44616046)
Where should I address the billion dollar check?
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by emp17344 on Saturday July 19, 2025 @11:08AM (#44616104)
My buddy did it 5 years ago. You wouldn’t know him, he lives in Canada.
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by esafak on Saturday July 19, 2025 @11:40AM (#44616432)
The dog ate mine. And the solution didn't fit in the margin, anyway.
[ Parent | on HN ]
Re:Not Even Bronze: Evaluating LLMs on 2025 International Ma... by souldeux on Saturday July 19, 2025 @11:08AM (#44616119)
my model goes to a different school
[ Parent | on HN ]