Will o3 perform as well on the FrontierMath holdout dataset as it does on the main set?

1kṀ14k

resolved Apr 23

Resolved

ALL

Background

OpenAI's o3 model reportedly achieves 25% accuracy on the FrontierMath benchmark, a significant achievement in mathematical problem-solving. However, it turns out they had access to the dataset while it was being created. Epoch AI, the creators of FrontierMath, are developing a holdout dataset specifically designed to test o3's capabilities without any prior exposure to the problems.

Resolution Criteria

This market will resolve YES if o3's performance on the FrontierMath holdout dataset is within 5 percentage points of its reported 25% accuracy on the main dataset (i.e., between 20-30% accuracy). It will resolve NO if:

The performance differs by more than 5 percentage points from the reported 25% accuracy
OpenAI declines to have o3 tested on the holdout dataset
The holdout dataset testing is not completed by December 31, 2025

Considerations

Elliot Glazer, lead mathematician at Epoch AI, believes OpenAI has no incentive to misrepresent their internal benchmarking but emphasizes the importance of independent verification
The holdout dataset is specifically being designed to prevent any potential advantages from prior exposure or overfitting
This will be one of the first major independent verifications of a leading AI model's mathematical capabilities

Math

IMO Grand Challenge

AI Benchmarks

Mechanistic interpretability

Machine Learning

Get

1,000

to start trading!

🏅 Top traders

#	Name	Total profit
1		Ṁ1,254
2		Ṁ357
3		Ṁ305
4		Ṁ272
5		Ṁ210

People are also trading

What will be the best performance on FrontierMath by December 31st 2025?

Will a Chinese-made AI beat o3's December score on Frontier Math by the end of 2025?

65% chance

By when will AI score >= 80% on FrontierMath

What will be o3's score on FrontierMath?

Will an AI score over 80% on FrontierMath Benchmark in 2025

21% chance

Will Alphaproof achieve >30% performance on the FrontierMath benchmark before 2026?

17% chance

Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?

60% chance

Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?

74% chance

Will any AI model score >80% on Epoch's Frontier Math Benchmark in 2025?

17% chance

Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?

Sort by:

I think this is kind of weird because it isn't the holdout set, but I think it should resolve no, since it's nowhere near what they claimed.

@NathanpmYoung Makes sense, but what does the "private" at the bottom of the graph mean? Is a private dataset different from a holdout dataset?

bought Ṁ150 NO

o3 scores only 10% on FrontierMath now.

filled a Ṁ100 NO at 37% order

@NathanpmYoung

Does this resolve NO?

https://www.lesswrong.com/posts/z8zPL2hBqTmx7Kf6J/frontiermath-score-of-o3-mini-much-lower-than-claimed

@FergusArgyll Epoch's numbers are not about the hold out dataset afaik

@Fay42 also that's about o3-mini, not o3

Is that 2024 for holdout set supposed to be 2025?

👀

All questions of overfitting etc aside, I'd bet it's probably tricky to norm the two sets given the nature of the problems. +-5% seems very plausible on that basis alone.