I’m still baffled that some people are bold enough to voluntarily posts those kind of most-of-the-time useless “benchmark” that will inevitably be riddled with errors.
I don’t know what pushes them. In the end you look like a clown more often than not.
Trying things casually out of curiosity isn’t harmful. I expect people understand that these kinds of blog posts aren’t rigorous science to draw foundational conclusions from.
And the errors are a feature — I learn the most from the errata!
