The Arc Prize Foundation says its new ARC-AGI-2 test stumps most AI models; humans get 60% of the questions right but GPT-4.5 and Claude 3.7 Sonnet score ~1% (Maxwell Zeff/TechCrunch)

https://ift.tt/9TFhxpD

Maxwell Zeff / TechCrunch:
The Arc Prize Foundation says its new ARC-AGI-2 test stumps most AI models; humans get 60% of the questions right but GPT-4.5 and Claude 3.7 Sonnet score ~1%  —  The Arc Prize Foundation, a nonprofit co-founded by prominent AI researcher François Chollet, announced in a blog post …

from Techmeme https://ift.tt/OujMP2W