iiRecord
Agentic AI Atlas · ARC-AGI 3
benchmark:arc-agi-3a5c.ai
II.
Benchmark overview

benchmark:arc-agi-3

Reference · live

ARC-AGI 3 overview

Interactive visual-reasoning benchmark from François Chollet / ARC Prize Foundation (2025). Agents play short novel grid-based games to test fluid intelligence and pattern induction over interactive environments rather than static IQ-style puzzles.

BenchmarkOutgoing · 4Incoming · 0

Attributes

displayName
ARC-AGI 3
homepageUrl
kind
interactive-reasoning
targetsKind
AgentVersion
description
Interactive visual-reasoning benchmark from François Chollet / ARC Prize Foundation (2025). Agents play short novel grid-based games to test fluid intelligence and pattern induction over interactive environments rather than static IQ-style puzzles.

Outgoing edges

applies_to2
covers2

Incoming edges

None.