AI engineers claim new algorithm reduces AI power consumption by 95%

Maybe I am just a natural skeptic, but whenever I see a headline that says 'method x reduces y by z%'; but when you read the text it instead says that optimizing some step 'could potentially reduce y by up to z%'; I am suspicious.

Why not publish some actual benchmarks that prove your claim in even a few special cases?

Because as disappointing as modern life is, you need clickbait headlines to drive traffic. You did the right thing by reading the article though, that's where the information is, not the title.