Michael D. Moffitt

Thank you to everyone who came out to the ARC-AGI-3 Launch Party last night Incredible room of people pushing AI forward ARC Prize 2026 competition is now open - let the games begin

One of the many reasons why ARC-AGI (as a bellwhether of fluid intelligence) is in a league of its own:

It's alive! This 3rd version of ARC-AGI represents an incredible amount of work from the ARC Prize team. Hundreds of games. Thousands of levels. Go build agents!

ARC-AGI-3 and ARC Prize 2026 are now live with $2,000,000 in prizes! As of today, version 3 is the world's only unsaturated agentic intelligence benchmark. Humans score 100% and frontier AI scores ~0%. Play here: arcprize.org/arc-agi/3 While no single version of ARC is definitionally AGI, our aim with the ARC-AGI Series is to continually produce useful scientific benchmarks which identify large remaining gaps between Humans and Frontier AI. At some point, we'll be unable to, and then we'll have AGI. Our new benchmark consists of over 100 novel game environments encompassing nearly 1,000 levels. Notably, test takers are given no explicit goals (other than to win) and must explore the environments to acquire goals, understand rules, develop strategy, and ultimately execute a plan to win. ARC-AGI-3 is a test of agentic intelligence. Beating this benchmark requires on-the-fly world modeling and continual learning to adapt to evolving environments. To score 100% AI must beat all of the games as efficiently as the human baseline (e.g., the number of actions taken to win). An ARC first, this gives us a formal comparison of AI reasoning efficiency vs humans. Version 3 carries classic ARC design principles: core knowledge priors only, private test sets to measure generalization, and it's fun! Every benchmark we release is an experiment and I believe this new version will provide strong signal towards increasingly autonomous AI agents. Prior versions of ARC held strong predictive power for important AI moments. Version 1 only saw progress with the release of AI reasoning models in late 2024 and Version 2 only began seeing progress with the advent of agentic coding models in late 2025. Version 3 is expected to signal when AI agents can become economically useful in more open-ended domains (beyond highly measurable domains like coding and math). There are a few other important design changes for ARC-AGI-3. The public set is now a "demonstration" set, not a training set. And unlike prior versions, the private set is now explicitly designed to be Out Of Distribution (non-IDD) from the public demo set. This is to mitigate targeting and because LLMs can now generalize over IDD splits using AI reasoning. Frontier models have made great progress over the past year. So much that several industry leaders have suggested we may already have AGI. Part of the ARC Prize Foundation mission is to provide accurate public sense finding and we strive to reduce false-positive claims. To this end, we've updated our testing policy. Going forward we will only verify scores outside of the official Kaggle competitions from AI systems with high commercial usage or are 100% open source. We're also adopting a stateless client scoring philosophy to ensure humans and AI are tested under identical conditions. The goal of these changes is to reduce the amount of developer-aware targeting (whether incidental or intentional) and provide clear signal if actual AGI progress has occurred. The Foundation also has a goal to inspire AI innovation which is most likely to come from the community. We've seen dozens of startups using ARC as a tool for showcasing their ideas - a few have fundraised serious capital based on their ARC results. To support this we're launching a new Community leaderboard. While scores for this leaderboard can't be Verified, and you should explicitly not trust these scores as an accurate measure of AGI progress, we will curate the best ideas and promote them. This year I expect we will see rapid progress on the ARC-AGI-3 Community leaderboard and the best ideas will eventually migrate into frontier models and onto the Verified leaderboard. Finally, we’ve partnered again with Kaggle to run two competition tracks for ARC-AGI-2 and ARC-AGI-3. This will be the last year for Version 2. When we launched the first ARC Prize back in 2024, I committed to running the Grand Prize until it was beaten. So for the ARC-AGI-2 track we will be paying out the Grand Prize to the best team, no matter what, in order to honor this commitment. In accordance with the Foundation mission, to win any prize money you must open-source a reproducible solution. We raised the standard for open source to include training. I'm excited to produce a truly open solution as a final send off for the ARC-AGI-1 and 2 format. Focus is now on ARC-AGI-3 (we've even started work on Versions 4 and 5). As always, I'm honored to have the opportunity to steward attention towards AGI progress. I'm also super grateful to the incredible ARC Prize team - including our core engineers, game designers, and human testers - led by @GregKamradt without whom we would not have this incredibly useful benchmark. See you on the leaderboard!

Announcing ARC-AGI-3 The only unsaturated agentic intelligence benchmark in the world Humans score 100%, AI <1% This human-AI gap demonstrates we do not yet have AGI Most benchmarks test what models already know, ARC-AGI-3 tests how they learn

ARC-AGI-3 is out now! We've designed the benchmark to evaluate agentic intelligence via interactive reasoning environments. Beating ARC-AGI-3 will be achieved when an AI system matches or exceeds human-level action efficiency on all environments, upon seeing them for the first time. We've done extensive human testing that shows 100% of these environments are solvable by humans, upon first contact, with no prior training and no instructions. Meanwhile, all frontier AI reasoning models do under 1% at this time.

The NeurIPS 2026 Call for Papers is now live: neurips.cc/Conferences/20… Abstracts are due May 4, 2026 (AOE), with full papers due May 6, 2026 AOE. Please review the key changes to submissions this year neurips.cc/Conferences/20…, as well as our new initiative for Strengthening Area Chair Engagement and Calibration at NeurIPS 2026 blog.neurips.cc/2026/03/23/ref…

How can we evaluate progress toward AGI as systems grow increasingly capable? In our new pre-print, we introduce a scientifically-grounded framework for mapping the cognitive capabilities of AI systems: storage.googleapis.com/deepmind-media…

ARC Prize Foundation is part of the @ycombinator W26 batch as the only non-profit. For Demo Day we’re shipping ARC-AGI-3, an interactive reasoning benchmark for the next era of agentic intelligence. ARC and YC are mission aligned that new ideas that push the frontier.

every known prime number is of the form n.

Excited to launch Gemini 3.1 Pro! Major improvements across the board including in core reasoning and problem solving. For example scoring 77.1% on the ARC-AGI-2 benchmark - more than 2x the performance of 3 Pro. Rolling out today in @GeminiApp, @antigravity and more - enjoy!

@MRBullMktEver @LynAldenContact Study history.

I guess I don't understand why @LynAldenContact is making a point that you can self custody your BTC but not your NVDA stock? The only reason you'd care about self custody of an asset is if you're a criminal and you're afraid your assets will be frozen. Why else would you care?

The ARC Prize north star is shining brighter than ever.

The new Gemini Deep Think is achieving some truly incredible numbers on ARC-AGI-2. We certified these scores in the past few days.

We are looking for brilliant deep learning researchers to help us solve program synthesis at @ndea. If you strongly feel like AGI should be capable of invention, not just automation, consider joining us. Apply here: ndea.com/jobs

@thinkingshivers Perfect candidate for an ARC-AGI-3 game! arcprize.org/arc-agi/3/

I made a simple puzzle game! Try to enclose the horse in the largest possible area with limited walls.

@GregKamradt Any chance we can get the ARC Prize website to render specific puzzles via URL again, like this? arcprize.org/play?task=543a… (I currently just get a blank page)

ARC Prize 2025 Winners Interviews Paper Award 3rd Place @LiaoIsaac91893 shares the story behind CompressARC - an MDL-based, single puzzle-trained neural code golf system that achieves ~20–34% on ARC-AGI-1 and ~4% on ARC-AGI-2 without any pretraining or external data.

@angeris Same energy.

updates on the michelson

@ethylene_66 It's all thanks to @divy93t! He made sure the event was sufficiently catered. 🙏

code golf workshop, 10人しか参加しないミニイベントかと思いきや、聴衆50人くらいいてひっくり返ってる