What's the saying, don't believe a metric unless you've invented it yourself?

'Our work demonstrates that several widely used [gene prediction] tools are neither accurate nor computationally efficient for the protein-coding sequence detection problem. In fact, just three of nine tools significantly outperformed a naive scoring scheme.'

https://www.biorxiv.org/content/10.1101/2024.05.16.594598v1

Standards

xkcd
@thatdnaguy @PhilippBayer it's kinda worse than this. I presume the competing XKCD standards are useful. These are tools people have been using for years that are provably sh!t -- one is little better than a random number generator, many others are no better than a stop-free scanner.