Skip to content

Top New Best Ask Show Jobs

HWE Bench: A new unbounded Benchmark for LLMs (GPT 5.5 is on top) | Better HN

HWE Bench: A new unbounded Benchmark for LLMs (GPT 5.5 is on top) (opens in new tab)

(hwebench.com)

6 pointsfesens11d ago3 comments

3 comments

fesensOP11d ago

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).

paulobeckhauser10d ago

Very nice!!

fabiofachini9211d ago

Amazing!

j / k navigate · click thread line to collapse