Development

ARC Prize declares its own benchmarks saturated

development2025-12-26

Claim

The ARC Prize Foundation declared ARC-AGI-1 and ARC-AGI-2 saturated, saying current tests can no longer bound frontier fluid intelligence, and moved the target to Millennium Problem complexity.

Reporting date: 2025-12-26 (not necessarily the event date)

Sources

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

Welcome to December 26, 2025 (theinnermostloop.substack.com)

Two days after a harness reached 75%, the test is retired by its authors. The replacement is open mathematics.

Knowledge graphopen in browser →

About

Reported in

Welcome to December 26, 2025

Actor

ARC Prize Foundation

Evidence for

Supersedes

A harness takes ARC-AGI-2 to 75% without touching the model

Referenced by

Cite or correct this record

Citation formatCitation text

ARC Prize declares its own benchmarks saturated
Innermost Loop KB — secondary record
Reporting date: 2025-12-26
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2025-12-26-arc-declares-saturation
Claim: The ARC Prize Foundation declared ARC-AGI-1 and ARC-AGI-2 saturated, saying current tests can no longer bound frontier fluid intelligence, and moved the target to Millennium Problem complexity.
Attributed sources:
- Welcome to December 26, 2025 — https://theinnermostloop.substack.com/p/welcome-to-december-26-2025
This citation does not imply independent verification of linked-source claims.

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