벤치마크 · reasoning

ARC-AGI 3

1 결과 1 모델

ARC Prize's third generation (2026): the agent must learn an unseen interactive game environment from scratch. Scores run far lower than — and are NOT comparable to — the static grid-puzzle ARC-AGI 1/2.

0 25 50 75 100 2026-07-17 Schema · 99 · 2026-07-17
Schema
타임라인
날짜 모델 점수 출처
2026-07-17 Schema 99.0% Moonshot, Kimi K3 출시; Schema harness, ARC-AGI 3에서 99% 달성