Source: ARC-AGI series and ARC-AGI-3 (ARC Prize Foundation)
ARC Prize pages describing the ARC-AGI series and ARC-AGI-3's move to interactive game environments scored on human action efficiency.
Contents
- What: official benchmark web pages
- Publisher: ARC Prize Foundation
- Date: accessed 2026-11-14
- Original: arcprize.org/arc-agi · arcprize.org/arc-agi/3
Summary
ARC-AGI (Chollet, 2019) defines intelligence as skill-acquisition efficiency on novel tasks, uses only core cognitive priors rather than cultural knowledge, and follows an “easy for humans, hard for AI” design rule. ARC-AGI-3 replaces static puzzles with interactive environments.
Key claims
- ARC-AGI-3 agents act in game environments with no natural-language instructions and must learn the rules by exploration.
- It measures learning efficiency, long-horizon planning with sparse feedback, and multi-step adaptation.
- Scoring is relative to human efficiency: 100% means beating every game as efficiently as humans.
- ARC Prize 2026 has closed; results are due 4 December 2026 (as of 2026-11-14). Kaggle hosts ARC-AGI-2 and ARC-AGI-3 competitions.