Benchmark family

ARC-AGI

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 2 definitions is resolved separately.

General reasoningAbstract reasoning

Definitions

Compare versions →

Newest first, following the recorded successor chain. Each definition is resolved against models separately.

BenchmarkARC-AGI-22
Active
Successor of ARC-AGI-1
Scale
1,000 tasks
Primary metric
Pass@2
Applicable models
0
BenchmarkARC-AGI-11
ActiveNewest in family
Scale
400 tasks
Primary metric
Pass@2
Applicable models
0

Family methodology

No family-level methodology recorded.

Across definitions

Tasks: None recorded
Sources: None recorded at family level
Last reviewed: 2026-09-22

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.