Research institute · Research orgs · San Francisco · Est. 2024
ARC Prize Foundation is a U.S.-based nonprofit focused on accelerating progress toward open AGI by creating and maintaining human-calibrated AI benchmarks, and by running open competitions that incentivize researchers to publish reproducible solutions. Its core mission is to measure and reduce the capability gap between humans and AI on tasks that are straightforward for people but remain difficult for advanced systems, using the ARC-AGI benchmark series as the central “north star.”
The organization’s work is organized around (1) open benchmarks/datasets and benchmarking software across the ARC-AGI series, (2) public leaderboards (including a “Verified” track intended to certify results on hidden evaluation sets), (3) the ARC Prize competitions that award prize money for open-source solutions, and (4) additional community resources/leaderboards to support ongoing work in the ARC-AGI ecosystem.
No curated programs yet. Check the careers page ↗.
OpenAI's GPT-6 Astra reaches state-of-the-art results on ARC-AGI-3
ARC Prize 2026: ARC-AGI-3 Milestone Prize #1Celebrating the top three submissions from our first ARC-AGI-3 milestone prize.
Analyzing GPT-5.5 & Opus 4.7 with ARC-AGI-3Analyzing GPT-5.5 & Opus 4.7 with ARC-AGI-3 AI benchmarks can be incredible tools, but they usually only tell you if a model passed or failed. With ARC-AGI-3, however, we can see the thought process *behind* the score, not just the outcome. This week we went through 160 replays a
Measuring Human Performance on ARC-AGI-3Measuring Human Performance on ARC-AGI-3 AGI is here when a system can learn like a human. However there is still a gap between what humans can learn and what AI can learn. ARC Prize Foundation exists to understand this gap. The ARC-AGI benchmarks are our tools for measuring it.
Announcing ARC-AGI-3ARC-AGI-3 is the first fully-interactive benchmark in the ARC-AGI series, featuring hundreds of handcrafted games with thousands of levels.
ARC Prize 2025 Results and AnalysisWinners, analysis, and interviews.
Announcing ARC Prize VerifiedARC-AGI benchmark test results you can trust.
ARC-AGI-3 Preview: 30-Day LearningsOne Month of Learnings Building Interactive Reasoning Benchmarks
The Hidden Drivers of HRM's Performance on ARC-AGIWe scored on hidden tasks, ran ablations, and found that performance from the Hierarchical Reasoning Model comes from an unexpected source
ARC Prize Foundation Statement on the US AI Action PlanARC Prize Response To AI Action Plan
We tested every major AI reasoning system. There is no clear winner.A technical analysis of frontier AI reasoning systems as of June 2025.
ARC-AGI-2 A New Challenge for Frontier AI Reasoning SystemsTechnical context and description of the ARC-AGI-2 Benchmark
ARC Prize Foundation reports ARC-AGI-3 performance results for OpenAI’s GPT-6 Astra and describes observed behaviors including constructing symbolic world models and tracking/preserving reasoning state (as described in the post’s harness context).
ARC Prize 2026: ARC-AGI-3 Milestone Prize #1ARC Prize Foundation announces the first ARC-AGI-3 milestone prize results (with $37.5K described) for top mid-competition open-source submissions to ARC-AGI-3, tied to a milestone through June 30, 2026.
Measuring Human Performance on ARC-AGI-3ARC Prize Foundation releases a human dataset for ARC-AGI-3, describing a controlled study of 458 participants and positioning the dataset as baseline evidence for human learning and solution strategies on ARC-AGI-3.
Announcing ARC-AGI-3ARC Prize Foundation announces the release of ARC-AGI-3 and describes it as an interactive, agentic benchmark with hundreds of interactive environments and thousands of levels; it also states ARC Prize 2026 is live with over $2M in prizes.
ARC Prize 2025 Results and AnalysisARC Prize Foundation publishes results and analysis from the ARC Prize 2025 competition and thanks leadership and participating labs, describing ongoing stewardship of ARC as a north star for AGI progress.
Announcing ARC Prize VerifiedARC Prize Foundation launches ARC Prize Verified to increase rigor by certifying scores on hidden ARC-AGI evaluation sets and adding an independent academic panel to audit the verification process; it also announces five new AI lab sponsors for ARC-AGI-3 development.