# Abstraction and Reasoning Corpus (ARC-AGI)

> Grid puzzles. Each one asks an AI to learn a new rule from just a few pairs.

**Field:** Artificial Intelligence  
**Category:** Evaluation & Benchmarks  
**Also known as:** ARC-AGI, ARC-AGI-2, ARC Prize

## Think of it like

It is like a puzzle book where each page has a new kind of puzzle. You must spot the trick from a few tries.

## Definition

ARC-AGI is a benchmark of puzzles made of small colored grids. Each task shows a few example pairs, an input grid and the output it turns into. The solver must find the hidden rule and build the output for a new grid. Every task is new, so memory does not help, only spotting the rule. François Chollet made it in 2019. Harder versions followed, ARC-AGI-2 in 2025 and ARC-AGI-3, where the puzzles are games.

## Example

One task shows three pairs of grids where every blue square turns red. The solver must apply that rule to a fourth grid, with every cell right.

## Why it matters

Most tests reward what a model already knows. This one tries to check how well it learns something new.

## Common mistake

Thinking a high score means a model is as smart as a person. It tests one skill, learning a rule from a few pairs.

## Three principles

- **Few examples.** Find the rule from a few pairs.
- **Exact answer.** Every cell must match.
- **Easy for people.** Hard for AI, by design.

## Related terms

- [AI Benchmark](https://learn.benibix.com/term/ai/ai-benchmark)
- [Artificial General Intelligence (AGI)](https://learn.benibix.com/term/ai/artificial-general-intelligence)
- [Reasoning Model](https://learn.benibix.com/term/ai/reasoning-model)
- [Humanity's Last Exam (HLE)](https://learn.benibix.com/term/ai/humanitys-last-exam)
- [Benchmark Saturation](https://learn.benibix.com/term/ai/benchmark-saturation)

![Two example pairs of small three by three grids, where each input's dark squares turn bright in the output. A third input grid points to an empty grid with a question mark.](https://learn.benibix.com/diagrams/ai5-arc-agi.svg)

---

Source: https://learn.benibix.com/term/ai/arc-agi
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
