ARC-AGI-1 A
AI benchmark · Reasoning
What is ARC-AGI-1?
ARC-AGI-1 measures how efficiently AI systems learn and generalize abstract rules from a few examples on 800 grid-based reasoning puzzles, compared with humans.
General capability mostly
“developed ARC-AGI-1 specifically as a novel benchmark designed to test the ability of AI systems to deal with reasoning problems they had not been prepared for.”
arcprize.org/arc-agi/1 ↗
Who built ARC-AGI-1
Led by François Chollet.
Paper: arxiv.org/abs/1911.01547 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Derived benchmarks
ARC-AGI-2 later version
Tier A
Widely used: a lab reports it, or 50 or more models are scored on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 106 models scored
- in curated RL directories (2 pts)
On X · mixed, moderate buzz, from 7 posts about ARC-AGI-1 in the last month
ARC-AGI-1 still appears in ARC Prize's verified score posts, but frontier models now score 96-98% on it, so attention has moved to ARC-AGI-2 and ARC-AGI-3.
How we got to tier A
- Adoption: 106 models scored. Tier A.
- On X: mixed, moderate buzz. “ARC-AGI-1 still appears in ARC Prize's verified score posts, but frontier models now score 96-98% on it, so attention has moved to ARC-AGI-2 and ARC-AGI-3.” No move.
- In curated RL directories: 2 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where ARC-AGI-1 sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.