Claude Opus 5 wins 10-LLM physics-sim tower-building benchmark

Each model placed 30 blocks through a noisy tool API — precise position or precise velocity, not both — across 5 seeds and 3 attempts; the score was what remained standing, with models keeping a notebook between attempts.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills