Benchmark

ARC-AGI-1

Measures: Grid puzzles from the original Abstraction and Reasoning Corpus: from a few input/output examples the model must produce the exact output grid for a new input.

Maintainer
ARC Prize Foundation (created by François Chollet)
Introduced
2019
Status
Active
Saturation
Saturated
Typical provenance
Independent
In scoring set
No

PaperOfficial leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.