Development

Problems are removed from a benchmark for being insufficiently notable

development2026-03-28

Claim

Epoch AI has begun removing problems from its FrontierMath benchmark after AI solutions exposed the problems themselves as insufficiently notable, while Harmonic reported its system powered the formalization of an Erdős problem just solved by a seventeen-year-old.

Reporting date: 2026-03-28 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to March 28, 2026 (theinnermostloop.substack.com)

The benchmark breaking before the model does.

Knowledge graphopen in browser →

Reported in

Welcome to March 28, 2026

Actor

Evidence for

Supersedes

A new benchmark returns frontier models to near zero

Referenced by

Cite or correct this record

Citation formatCitation text

Problems are removed from a benchmark for being insufficiently notable
Innermost Loop KB — secondary record
Reporting date: 2026-03-28
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-03-28-epoch-retires-problems-as-unworthy
Claim: Epoch AI has begun removing problems from its FrontierMath benchmark after AI solutions exposed the problems themselves as insufficiently notable, while Harmonic reported its system powered the formalization of an Erdős problem just solved by a seventeen-year-old.
Attributed sources:
- Welcome to March 28, 2026 — https://theinnermostloop.substack.com/p/welcome-to-march-28-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.