Before 2026, What will be true of OpenAI's Claimed IMO Gold Performance?
8
175Ṁ256Dec 31
90%
At least one former IMO medalist will review the model's answers and claim it did not actually achieve Gold
66%
The model that achieved it was trained with a new reinforcement learning algorithm
50%
The model that achieved it could earn at least bronze using no more than 100,000 reasoning tokens per question
41%
It was achieved with the same model OpenAI used to get second place in AtCoder
34%
The breakthrough is mostly the result of superior test-time scaling methods
34%
I will consider the techniques used to achieve it at least as big of a breakthrough as strawberry
24%
It was achieved by a model that does not use a standard transformer architecture
Update 2025-07-21 (PST) (AI summary of creator comment): A claim will only be considered valid if the person making it can prove to the creator that they are a former IMO medalist.
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000People are also trading
Related questions
Will OpenAI become nothing by 2030?
AI IMO 2025: How many AI labs announce a Gold performance at the IMO in 2025?
Will OpenAI o1 (or any direct iteration like o3) get gold on any International Math Olympiad by the end of 2025?
25% chance
Will OpenAI claim that it has achieved AGI in 2025?
5% chance
Will AI get BOTH gold and either bronze or silver on the IMO by end of 2025?
84% chance
Will OpenAI still be considered one of the top players in AI by end of 2025
98% chance
An AI model published prior to the 2025 IMO achieves gold medal performance
9% chance
Will an AI get gold on this Olympiad by the end of 2025?
What will be true of the gold-IMO-medal-winning internal OpenAI model? [Add Answers]
Will AI win a gold on IMO before it wins a gold on IOI?
98% chance