What will be the best performance on FrontierMath Tier 4 by December 31st 2025?
10
1kṀ990
Dec 31
18%
0% - 10%
38%
10 - 20%
27%
20 - 30%
6%
30 - 40%
3%
40 - 50%
1.8%
50 - 60%
1.8%
60 - 70%
1.8%
70 - 80%
1.8%
80 - 90%
1.8%
90 - 100%

The best performance by an AI system on FrontierMath Tier 4 as of December 31st 2025. See https://epoch.ai/frontiermath, under the section Tier 4, for results accepted for the purpose of this market. The "performance" is measured in terms of Pass@1 Accuracy.

At market creation (and day of the official announcement of the benchmark), the best model is o4-mini (high), with a score of 6.25%.

See also best performance on FrontierMath Tier 1-3:

AI
Technical AI Timelines
AI Benchmarks
AI 2025 Forecasting Survey by AI Digest
Get
Ṁ1,000
to start trading!

People are also trading

What will be the best performance on FrontierMath by December 31st 2025?
Will any AI model achieve > 40% on Frontier Math before 2026?
55% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
60% chance
Top FrontierMath score in 2025?
53.5
Will an AI score over 80% on FrontierMath Benchmark in 2025
8% chance
In what year will Al achieve 95% or higher score on the FrontierMath benchmark?
Will Al achieve 95% or higher score on the FrontierMath benchmark before 2030?
63% chance
Before what year will Al achieve 85% or higher score on the FrontierMath benchmark?
In what year will Al achieve 95% or higher score on the FrontierMath benchmark?
2031
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
55% chance
Sort by:
bought Ṁ50 YES

GPT-5 (high) got one more problem than previous models, for a score of 8.3% (4/48).

My intuition is that you can't get much better results on this benchmark just by scaling current methods and that no one will implement a new method before end of 2025.

I think there's still a fair bit it can be pushed but I agree probably no one will implement a new method before end of 2025. do you think the method that first gets 30% will use a new method?

@Bayesian Yeah. But I didn't do too much research on the questions I just know they are unique from trainable datasets, and require a lot of reasoning steps. I think we need a new method that will help AIs better generalize their learnings and skills from different domains.

People are also trading

What will be the best performance on FrontierMath by December 31st 2025?
Will any AI model achieve > 40% on Frontier Math before 2026?
-7% 1d55% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
60% chance
Top FrontierMath score in 2025?
53.5
Will an AI score over 80% on FrontierMath Benchmark in 2025
8% chance
In what year will Al achieve 95% or higher score on the FrontierMath benchmark?
Will Al achieve 95% or higher score on the FrontierMath benchmark before 2030?
63% chance
Before what year will Al achieve 85% or higher score on the FrontierMath benchmark?
In what year will Al achieve 95% or higher score on the FrontierMath benchmark?
2031
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
55% chance
© Manifold Markets, Inc.•Terms•Privacy