Austin avatar
closes 
Jan 1, 2026
Will an AI get gold on any International Math Olympiad by 2025?
31%
chance
An opportunity to join in on https://www.lesswrong.com/posts/sWLLdG6DWJEy3CH7n/imo-challenge-bet-with-eliezer Eliezer has this at >16%; Paul at <8%. Resolves to YES if either Eliezer or Paul acknowledge that an AI has succeeded at this task. Related market: https://manifold.markets/MatthewBarnett/will-a-machine-learning-model-score-f0d93ee0119b
Gigacasting avatar
Gigacasting is predicting NO at 32% 2 days ago
0
Gigacasting avatar
Gigacasting is predicting NO at 32% 2 days ago
0
Gigacasting avatar
Gigacasting bought M$50 of NO3 days ago
0
jack avatar
Jack is predicting NO at 44% 3 days ago
0
Gigacasting avatar
Gigacasting bought M$50 of NO3 days ago
0
Gigacasting avatar
Gigacasting bought M$250 of NO3 days ago
0
jack avatar
Jack bought M$20 of YES3 days ago
0
Gigacasting avatar
Gigacasting is predicting NO at 34% 3 days ago
0
Gigacasting avatar
Gigacasting bought M$12 of NO3 days ago
0
Gigacasting avatar
Gigacasting bought M$180 of NO3 days ago
0
Accountdeletionrequested avatar
Account deletion requested is predicting NO at 43% a month ago
0
jack avatar
Jack is predicting NO at 36% 3 days ago
0
Gigacasting avatar
Gigacasting bought M$50 of NOa month ago
0
Gigacasting avatar
Gigacasting is predicting NO at 41% a month ago
0
JoyVoid avatar
joy_void_joy bought M$465 of YESa month ago
0
JoyVoid avatar
joy_void_joy is predicting YES at 53% a month ago
0
JamesGiammona avatar
Given progress with Minerva, I think this should be higher. https://twitter.com/alewkowycz/status/1542559176483823622
0
Sinclair avatar
See also https://www.metaculus.com/questions/6728/ai-wins-imo-gold-medal/ currently distribution is 25% by 2026, 50% by 2029, 75% by 2037
0
MP avatar
I don't understand how this bet is settled. I once worked in the IMO (during undergrad, I'm not that smart) and the exam itself is subject to significant subjectivity. 100 teachers take two days LITERALLY locked into a hotel to correct the exams. The only way I think a bet like this could be solved is if the IMO were to agree to send a solution made by an AI to the examiners. I know that THIS market is settled however Eliezer and Paul settle their bets but just sharing my thoughts.
0
Conflux avatar
Conflux bought M$50 of NO3 months ago
This is an Austin market, I doubt it will resolve based on a fake IMO.
0
NN avatar
N. N. bought M$100 of NO7 months ago
Agree w/ Lorenzo, current price is crazy.
0
Lorenzo avatar
Lorenzo bought M$129 of NO7 months ago
No idea what's going on in this market. Eliezer and Paul clearly agree on what the IMO is. Curious about the reasoning of people buying this much YES (well above Elizier >16%)
0
Duncan avatar
Duncan bought M$1 of YES7 months ago
The IMO is probably specific enough, and neither of the founding bettors would question this. Neither this nor the LessWrong post actually uses the trademarked term "International Mathematical Olympiad" though.
0
MP avatar
@Duncan any imo likely means 2023,2024 or 2025 IMO
0
Duncan avatar
Duncan bought M$1 of YES7 months ago
I guess I'd have to get EY's buy-in first, and that's probably a no-go.
0
Duncan avatar
Duncan bought M$1 of YES7 months ago
So, if I were to set up a math Olympiad with Canadian and American 1st graders, and an AI beat them, would that qualify?
0
Lorenzo avatar
Lorenzo bought M$13 of NO7 months ago
Why is this market at 81% if we have Paul at <8% and Eliezer at >16%? I feel that I'm missing something about the resolution, but still 81% seems high
0

Play-money trading

Mana (M$) is the play-money used by our platform to keep track of your trades. It's completely free for you and your friends to get started!