NishMath

The ARC Prize Foundation has launched ARC-AGI-2, a new AI benchmark designed to challenge current foundation models and track progress towards artificial general intelligence (AGI). Building on the original ARC benchmark, ARC-AGI-2 blocks brute force techniques and introduces new tasks intended for next-generation AI systems. The goal is to evaluate real progress toward AGI by requiring models to reason abstractly, generalize from few examples, and apply knowledge in new contexts, tasks that are simple for humans but difficult for machines.

The Foundation has also announced the ARC Prize 2025, a competition running from March 26 to November 3, with a grand prize of $700,000 for a solution achieving an 85% score on the ARC-AGI-2 benchmark's private evaluation dataset. Early testing results show that even OpenAI's top models experienced a significant performance drop, with o3 falling from 75% to approximately 4% on ARC-AGI-2. This highlights how the new benchmark significantly raises the bar for AI tests, measuring general fluid intelligence rather than memorized skills.

ImgSrc: dataphoenix.inf

References :

• RunPod Blog: The race toward artificial general intelligence isn't just happening behind closed doors at trillion-dollar tech companies. It's also unfolding in the open—in research labs, Discord servers, GitHub repos, and competitions like the ARC Prize. This year, the ARC Prize Foundation is back with ARC-AGI-2
• Data Phoenix: The ARC Prize Foundation has officially released the ARC-AGI-2 to challenge current foundation models and help track progress towards AGI. Additionally, the Foundation has opened the ARC Prize 2025, running from Mar 26 to Nov 3, with a $700K Grand Prize for an 85% scoring solution on the ARC-AGI-2.
• THE DECODER: The new AI benchmark ARC-AGI-2 significantly raises the bar for AI tests. While humans can easily solve the tasks, even highly developed AI systems such as OpenAI o3 clearly fail. The article appeared first on .
• eWEEK: The newest AI benchmark, ARC-AGI-2, builds on the first iteration by blocking brute force techniques and designing new tasks for next-gen AI systems. The post appeared first on .

Classification:

• HashTags: #ARCAGI2 #AGI #AIBenchmark
• Company: ARC Prize Foundation
• Target: AI Researchers
• Product: ARC-AGI-2
• Feature: AGI Benchmarking
• Type: AI
• Severity: Informative