Development

The best model reaches 1.5% of human efficiency on ARC-AGI-3

development2026-06-02

Claim

Opus 4.8 posted a state-of-the-art 1.5% of human efficiency on ARC-AGI-3, tripling GPT-5.5's score and showing that the gap between frontier models is now measured in multiples per quarter.

Reported metric: 1.5%

Reporting date: 2026-06-02 (not necessarily the event date)

Sources

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

Welcome to June 2, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to June 2, 2026

Actor

Evidence for

Supersedes

The safest frontier model is also the strongest

Referenced by

Cite or correct this record

Citation formatCitation text

The best model reaches 1.5% of human efficiency on ARC-AGI-3
Innermost Loop KB — secondary record
Reporting date: 2026-06-02
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-06-02-one-and-a-half-percent-of-a-human
Claim: Opus 4.8 posted a state-of-the-art 1.5% of human efficiency on ARC-AGI-3, tripling GPT-5.5's score and showing that the gap between frontier models is now measured in multiples per quarter.
Attributed sources:
- Welcome to June 2, 2026 — https://theinnermostloop.substack.com/p/welcome-to-june-2-2026
This citation does not imply independent verification of linked-source claims.

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