AI Models Struggle with Bongards

This is a news story, published by The Debrief, that relates primarily to Claude news.

Claude news

For more Claude news, you can click here:

more Claude news

News about Ai research

For more Ai research news, you can click here:

more Ai research news

The Debrief news

For more news from The Debrief, you can click here:

more news from The Debrief

About the Otherweb

Otherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about

true AI comprehension

. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest visual reasoning news, elementary visual concepts news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!

visual concepts

The Debrief

•

New study reveals surprising gap in AI vision-language models’ reasoning capabilities

Summary

Nutrition label

81% Informative

A new study has revealed a surprising gap in the reasoning capabilities of today ’s most advanced AI vision-language models.

Researchers from various European institutions evaluated advanced Vision-Language Models (VLMs), such as GPT-4o and Claude , against a suite of classic puzzles called Bongard problems.

Humans performed best in the existence” (presence or absence of a feature) and spatial’ (spatial orientation) categories, with scores over 90% .

The findings challenge assumptions about AI ’s ability to mirror human cognition and raise critical questions about the adequacy of standard benchmarks for evaluating AI performance.

Translating Bongard problems to real-world scenarios might help AI models develop better perceptual and cognitive abilities.

As AI evolves, overcoming these perceptual limitations will be essential for creating systems that can interact with the world as seamlessly as humans do.

VR Score

Informative language

Neutral language

Article tone

formal

Language

English

Language complexity

Offensive language

not offensive

Hate speech

not hateful