ModelRefs / ARC-AGI 2 Leaderboard
ARC-AGI 2 Leaderboard
Second-generation ARC Prize evaluation suite (2025). Current leaders, methodology, and citation sources for ARC-AGI 2.
Overview
Second-generation ARC Prize evaluation suite (2025).
How it is measured: Pass@2 on private set; tougher abstraction puzzles.
How this benchmark is scored
| Category | reasoning |
|---|---|
| Maximum score | 100 % solved |
| Direction | Higher is better |
Primary source: https://arcprize.org/
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to ARC-AGI 2 Leaderboard.
Frequently asked questions
What does the ARC-AGI 2 benchmark measure?
Second-generation ARC Prize evaluation suite (2025).
What is the methodology?
Pass@2 on private set; tougher abstraction puzzles.
Which AI model is the current ARC-AGI 2 leader?
Gemini 3 Pro (Google) currently leads with 31.1 % solved.