ARC-AGI-2

AI benchmark · Reasoning

Domains
Reasoning
Data source
benchlm-benchmarks
Snapshot

Open benchmark ↗benchlm.ai/benchmarks/arcAgi2

About ARC-AGI-2

A benchmark measuring fluid intelligence and novel abstract reasoning through visual grid puzzles. Models must identify patterns in input-output pairs and generate the correct output for unseen inputs. Considered the hardest public reasoning benchmark — average individual human performance is 66%.

Where ARC-AGI-2 sits

Its domains, and the nearest entries sharing them. Click any node to open its page.

Select a node to trace its connections. Zoom in for more space; drag to pan.

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-09-21 snapshot.