---
id: "2026-03-25-arc-agi-3-launch"
url: "https://postcutoff.com/e/2026-03-25-arc-agi-3-launch/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-03-25"
date_precision: day
category: benchmark
importance: 4
confidence: medium
status: [Partly confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-03-25-arc-agi-3-launch/

# ARC Prize launches ARC-AGI-3, an interactive game benchmark where frontier AI scored under 1%

The ARC Prize Foundation launched ARC-AGI-3 on 2026-03-25: novel turn-based game environments with no instructions, measuring skill-acquisition efficiency. In the preview humans solved 100% of environments while frontier LLMs scored below ~0.4% (best purpose-built agent 12.58%); ARC Prize 2026 on Kaggle offers $850K including a $700K grand prize for 100%.

## 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.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [ARC-AGI-3](https://arcprize.org/arc-agi/3) (arcprize.org, official)
2. [ARC Prize 2026 — ARC-AGI-3 competition](https://arcprize.org/competitions/2026/arc-agi-3) (arcprize.org, official)
3. [ARC-AGI-3 paper (arXiv 2603.24621)](https://arxiv.org/pdf/2603.24621) (arxiv.org, paper)
4. [Kaggle leaderboard](https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-3/leaderboard) (kaggle.com, discussion)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2026-09-03: [GPT-6 Astra scores 62.7% on ARC-AGI-3, outacting humans on 96% of levels](https://postcutoff.com/e/2026-09-03-arc-agi-3-gpt-6-astra/index.md)