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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.