ARC Prize

2 min read Original article ↗

Top AI Leaders and Partners

OpenAI logoGoogle logoxAI logoAnthropic logo

ARC Prize is a provider of AI benchmarks to NIST’s Center for AI Standards and Innovation (CAISI)

Low-Noise, High-Signal AGI Benchmarks

We build scientifically grounded benchmarks that reveal the gap between what's easy for humans, hard for AI.

ARC-AGI has repeatedly identified key inflection points in AI progress, including the emergence of reasoning systems and the rise of capable AI agents.

Pinpointing precise changes in AI capabilities

New ideas still needed for AGI.

While AI has made tremendous progress, ARC-AGI shows us scaling alone will not reach AGI.

Our mission is simple: guide research, accelerate progress, and ensure the path to AGI remains open and accessible to all.

We define AGI as a system that can match the learning efficiency of humans.

Introducing ARC-AGI-3. The world's only unbeaten benchmark that measures agentic intelligence.

The gap between human and AI intelligence

Research

ARC-AGI Benchmark Series

Trusted by the world's leading AI labs and top academic researchers, explore the only benchmark that measures fluid intelligence. It's easy for humans, hard for AI.

Over $2M in prizes. 3 tracks. Get started.

Prize

Big ideas. Big money.

Get rewarded for open sourcing novel progress. In partnership with Kaggle, over $2M is up for grabs.

ARC Prize Co-Founders Mike Knoop and François Chollet

Foundation

Founder Message

“AGI is the most important technology humanity will create, and we believe it is achievable in our lifetime. But ARC shows us we still need new ideas. Maybe they'll come from you?”

Mike Knoop (Zapier, Ndea) & François Chollet (Keras, Ndea, ARC-AGI)