Development

A model beats an ARC-AGI-3 game and hits 92.5% on ARC-AGI-2

development2026-07-10

Claim

Sol became the first model to beat an ARC-AGI-3 game and hit 92.5% on ARC-AGI-2 at a tenth of a three-month-old model's cost, while Luna does GPT-5.5's knowledge work at 10% of the price and Epoch suspects Sol is 5.5-sized, making the gains pure algorithm.

Reported metric: 92.5%

Reporting date: 2026-07-10 (not necessarily the event date)

Sources

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

Welcome to July 10, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to July 10, 2026

Actor

Evidence for

Supersedes

A model completes over half of real workflow objectives without breaking rules

Referenced by

Cite or correct this record

Citation formatCitation text

A model beats an ARC-AGI-3 game and hits 92.5% on ARC-AGI-2
Innermost Loop KB — secondary record
Reporting date: 2026-07-10
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-07-10-ninety-two-percent-on-arc-agi-2-at-a-tenth-the-cost
Claim: Sol became the first model to beat an ARC-AGI-3 game and hit 92.5% on ARC-AGI-2 at a tenth of a three-month-old model's cost, while Luna does GPT-5.5's knowledge work at 10% of the price and Epoch suspects Sol is 5.5-sized, making the gains pure algorithm.
Attributed sources:
- Welcome to July 10, 2026 — https://theinnermostloop.substack.com/p/welcome-to-july-10-2026
This citation does not imply independent verification of linked-source claims.

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