Hacker News new | ask | show | jobs
HWE Bench: A new unbounded Benchmark for LLMs (GPT 5.5 is on top) (hwebench.com)
6 points by fesens 40 days ago
3 comments

Current benchmarks have ceilings, usually 100%. This benchmark aims to be a long lasting, high correlation with the ability to solve real world problems and follow complex instructions, and unbounded (meaning it can always go higher).
Very nice!!
Amazing!