ARC Prize launches ARC-AGI-3, an interactive game benchmark where frontier AI scored under 1%
Partly confirmed
Importance: major (4 of 5)The takeaway
The ARC Prize Foundation launched ARC-AGI-3 on 2026-03-25: novel turn-based game environments with no instructions, measuring skill-acquisition efficiency.
Status
- Claim
Partly confirmed
- Our reporting
- Medium confidence
- Importance
- Major (4 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- Launched 2026-03-25 at Y Combinator, San Francisco
- Format: interactive environments; agents must learn rules by acting, with sparse feedback and no natural-language instructions
- Developer preview: humans 100%; GPT-5.4, Claude Opus 4.6, Grok 4.2 scored 0%-0.37%; best preview agent 12.58% (secondary source)
- ARC Prize 2026: $850K pool; $700K grand prize; milestone deadlines 2026-06-30 and 2026-09-30; solutions must be open-sourced
- By July: GPT-5.6 7.78%, Claude Opus 5 30.16% (ARC Prize leaderboard)
What happened
ARC-AGI-3 moved the ARC series from static grid puzzles to interactive games to test exploration, planning and learning from experience.
Why it matters
It was designed as the hardest-to-game AGI benchmark of 2026; within six months it was largely cracked (see GPT-6 Astra entry), illustrating the pace of agentic progress.
Sources
4 sources from 3 sites. Numbers match the chips in the text.
4 sources: 3 primary, 1 reaction
Primary
- ARC-AGI-3arcprize.org, official
- ARC Prize 2026 — ARC-AGI-3 competitionarcprize.org, official
- ARC-AGI-3 paper (arXiv 2603.24621)arxiv.org, paper
Reactions
- Kaggle leaderboardkaggle.com, discussion
Changes
- Filed