PulseAugur
EN
LIVE 03:45:22

AI models falter on visual reasoning puzzles, solving only 18% of NYT Connections

By PulseAugur Editorial · [1 sources] ·

AI models continue to exhibit significant weaknesses in spatial reasoning and visual puzzle-solving capabilities. Recent evaluations in late 2024 indicated that leading AI models could only solve approximately 18% of New York Times Connections puzzles. This highlights a persistent challenge for AI development in understanding and manipulating visual information. AI

IMPACT Highlights ongoing limitations in AI's ability to perform complex visual and spatial reasoning tasks.

RANK_REASON The cluster discusses a benchmark result for AI models on specific types of puzzles, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI models falter on visual reasoning puzzles, solving only 18% of NYT Connections

How we ranked this

Signal score
18 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster discusses a benchmark result for AI models on specific types of puzzles, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    AI models struggle with spatial reasoning puzzles like mental rotation, and visual puzzles remain a weak spot. In late 2024, top models solved only 18% of New Y

    AI models struggle with spatial reasoning puzzles like mental rotation, and visual puzzles remain a weak spot. In late 2024, top models solved only 18% of New York Times Connections puzzles. Source: MIT Technology Review AI https://www. technologyreview.com/2026/08/2 6/1141952/pu…

    LINKS technologyreview.com/…/puzzles-ai-models-…

RELATED ENTITIES

RELATED TOPICS