Map / Core AI / Benchmarks & Leaderboards / ARC-AGI-2

ARC-AGI-2

Stress-tests efficiency and capability of state-of-the-art AI reasoning systems

CuratedAgent & General Benchmarks

I use this adds ARC-AGI-2 to your stack and finds people with similar stacks. Every mark feeds the counts on Pulse. Sign in to mark it.

No ratings yet

Who uses it

0 use this

0use it now

0tried it, dropped it

0want to try

Nobody has marked it yet. Press I use this, Tried it or Want to try to be the first.

Ratings

Only from people who use it or tried it

No ratings yet

The first rating comes from someone who uses ARC-AGI-2 or tried it.

Use ARC-AGI-2?

What it does

ARC-AGI-2 is a reasoning benchmark from ARC Prize made of visual grid puzzles that people solve readily but AI systems find hard. Each task asks the solver to infer a transformation rule from a few examples, testing symbolic interpretation, compositional reasoning and rules that change with context. Every task was solved by human testers, and results report cost per task alongside accuracy.

Alternatives on the map

All 26 alternatives

Benchmarks & Leaderboards, starting with the other Agent & General Benchmarks.

Compare with

People who use it also use

Not enough marks yet to tell. When people who use ARC-AGI-2 mark the rest of their stack, it shows up here.

Open website