ainewsblitz.com

Breaking

New Benchmark Tests 10 LLMs on Building Physical Towers, and Claude Opus 5 Comes Out on Top

New Benchmark Tests 10 LLMs on Building Physical Towers, and Claude Opus 5 Comes Out on Top
  • Research & Papers
  • Foundation Models
  • AI Agents

A developer has built an unconventional benchmark that pits ten large language models against each other inside a browser-based physics simulation, asking each to stack basic blocks into the tallest stable tower it can manage. The test, dubbed TowerBench, moves the evaluation of AI beyond static text or image questions and into a domain where gravity, friction, and center-of-mass errors carry real consequences, with Anthropic's Claude Opus 5 narrowly taking the top spot.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,929 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year