ARC-AGI
arcprize.org- Category
- Developer Tools
- Type
- TOOL
- GitHub
- 65 stars
- Added
- Jul 31, 2026
About
Measures skill acquisition and generalization on novel abstract tasks, including interactive agentic environments in ARC-AGI-3.
Why it made the leaderboard
Benchmark results are decision inputs for choosing models and agent harnesses; follow the methodology and current leaderboard, not a single headline score.
Tags
benchmarkreasoninggeneralizationagentic intelligence
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.