Will an LLM score >=85% on FrontierMath Tier 4 before 2028?

12

Ṁ100Ṁ708

resolved Jun 13

Resolved

YES

1H

6H

1D

1W

1M

ALL

FrontierMath: LLM Benchmark for Advanced AI Math Reasoning | Epoch AI

This market will be resolved as YES if the score of any LLM on the Tier 4 leaderboard will be 85.0% or higher before Jan 1, 2028.

Note that confidence intervals are ignored for the purpose of this market. For example, 85.0%±10.0% counts and the market will be resolved, whereas 80.0%±10.0% doesn't count. Also, Tiers 1-3 are not relevant for this market.

Update 2026-06-13 (PST) (AI summary of creator comment): The creator is resolving this market YES based on Claude Fable 5 (max) achieving >85% on Tier 4 v2 (a revised version of FrontierMath introduced after methodology changes corrected errors in the original problems).

Market context

Get

1,000

to start trading!

🏅 Top traders

#	Trader	Total profit
1		Ṁ27
2		Ṁ19
3		Ṁ14
4		Ṁ12
5		Ṁ10

Sort by:

I will be resolving this market as "YES". This market was made before the change in FrontierMath's methodology, and back then the highest score on Tier 4 was <50%. However, many problems had errors, which is why Tier 4 v2 was introduced, and Claude Fable 5 (max) achieves >85% on Tier 4 v2.

Epoch AI (@EpochAIResearch) on X

Epoch AI (@EpochAIResearch) on X

FrontierMath: Tiers 1–4 (v2) is live. We concluded an audit that addressed errors in 42% of problems. Rankings are similar but scores are higher across the board. The current leaders are GPT-5.5 (xhigh) with 85% on Tiers 1–3 and Google’s AI co-mathematician with 76% on Tier 4. https://t.co/DH9nhpKH0N

People are also trading

What will be the best FrontierMath Tier 4 score by Dec 31, 2026?

Will an LLM score >=95% on SimpleBench before 2028?

Will the highest-scoring LLM on Dec 31, 2026 show <10% improvement over 2025's best average benchmark performance?

Will a LLM trained with FP4 have frontier-level performance before 2028?

Will an LLM be able to solve the Self-Referential Aptitude Test before 2027?

Will Al achieve 95% or higher score on the FrontierMath benchmark before 2030?

Will a frontier-level diffusion LLM exist by 2028?

Frontier LLM mobile apps can be backgrounded mid reasoning in November 2026?

In what year will Al achieve 95% or higher score on the FrontierMath benchmark?

Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?

Related questions

What will be the best FrontierMath Tier 4 score by Dec 31, 2026?

Will an LLM score >=95% on SimpleBench before 2028?

Will the highest-scoring LLM on Dec 31, 2026 show <10% improvement over 2025's best average benchmark performance?

Will a LLM trained with FP4 have frontier-level performance before 2028?

Will an LLM be able to solve the Self-Referential Aptitude Test before 2027?

Will Al achieve 95% or higher score on the FrontierMath benchmark before 2030?

Will a frontier-level diffusion LLM exist by 2028?

Frontier LLM mobile apps can be backgrounded mid reasoning in November 2026?

In what year will Al achieve 95% or higher score on the FrontierMath benchmark?

Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?