Just announced an deep dive blog post with findings about an evaluation benchmark on software development quality. Here is a thread to the most important findings https://twitter.com/zimmskal/status/1786012661815124024 Blog post is on https://symflower.com/en/company/blog/2024/dev-quality-eval-...

What i am working next: is actually the next version of that eval. The assessments can be improved in lots of ways and there are much more cases coming.