Benchmark · reasoning

ARC-AGI 3

1 نتائج 1 نماذج

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
الجدول الزمني
التاريخ النموذج النتيجة المصدر
2026-07-17 Schema 99.0% مونشوت تطلق Kimi K3؛ Schema harness يحقق 99% على ARC-AGI 3