Benchmark

ARC-AGI-1

Sources

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

Welcome to December 12, 2025 (theinnermostloop.substack.com)

Tracked here mainly by cost per task, which is where the deflation shows.

Development timeline

Newest reporting dates first. Reporting dates may differ from event dates.

2026-09-30: The cost of a fixed ARC-AGI-1 score reportedly falls sharply

2025-12-26: ARC Prize declares its own benchmarks saturated

2025-12-23: Universal Reasoning Models hit 40% on ARC-AGI with an eighth the parameters

2025-12-18: Gemini 3 Flash matches a year-old frontier ARC-AGI score at 500x lower cost

2025-12-12: Reasoning cost on ARC-AGI-1 falls 390x in a year

Knowledge graphopen in browser →

Referenced by

Cite or correct this record

Citation formatCitation text

ARC-AGI-1
Innermost Loop KB — secondary record
Reporting date: unknown
KB permalink: https://nicholsn.github.io/innermost-loop-kb/benchmarks/arc-agi-1
Attributed sources:
- Welcome to December 12, 2025 — https://theinnermostloop.substack.com/p/welcome-to-december-12-2025
This citation does not imply independent verification of linked-source claims.

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