Print-friendly view · use your browser's Save as PDF option (Cmd/Ctrl-P) to attach this article to a brief.
ARC-AGI v2
ARC-AGI-V2 · general reasoning benchmark · 2025
Source: https://policywindow.org/wiki/arc-agi-v2
Generated 2026-07-09T20:39:49 UTC
Summary
Abstract reasoning over visual grids. Each task requires inferring the transformation rule from 2-3 examples.
At a glance
- Score range
- 0–100 % solved
- Contamination risk
- low
- Methodology URL
- https://arcprize.org/
- Saturation status
- active
Details
v2 launched 2025-03 with harder tasks designed to remain unsolvable by pure pattern matching. $1M public prize for >85% on private set. Currency (2026-06-21): Frontier moved well past the article's top figure of ~37.6% (Late-2025 Claude Opus 4.5) — ARC-Prize-verified SOTA reached 54% ($30.57/task, Poetiq, semi-private, verified Dec 5 2025), and by June 2026 vendor/aggregator-reported public-set scores cluster far higher (GPT-5.5 ~85%, GPT-5.4 Pro 83.3%, Gemini 3.1 Pro 77.1%, Claude Opus 4.7 Adaptive 75.8% per BenchLM); the $700K Grand Prize (private set, >=85% with efficiency constraint) remains UNCLAIMED and ARC Prize 2026 now offers $2M total.
How to cite this article
APA
Policy Window. (2025). ARC-AGI v2 [Wiki article — Benchmark]. https://policywindow.org/wiki/arc-agi-v2
Chicago
Policy Window. 2025. "ARC-AGI v2." Wiki article (Benchmark). https://policywindow.org/wiki/arc-agi-v2.
Harvard
Policy Window (2025) 'ARC-AGI v2', Wiki article — Benchmark, available at: https://policywindow.org/wiki/arc-agi-v2.
OSCOLA
Policy Window, 'ARC-AGI v2' (Wiki article — Benchmark, 2025) <https://policywindow.org/wiki/arc-agi-v2> accessed [date].
BibTeX
@misc{policywindow-arc-agi-v2,
title = {ARC-AGI v2},
author = {Policy Window},
year = {2025},
howpublished = {ARC-AGI-V2 (2025)},
url = {https://policywindow.org/wiki/arc-agi-v2},
note = {Primary source: https://arcprize.org/}
}