feat: better evaluation scripts

[juanjoDiaz]

I had this for a while sitting on my machine.
A revamp of the evaluation scripts so changes are really simple to evaluate.

We can iterate if you want to do further improvements 🙂

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 96.62%. Comparing base (ef1c103) to head (fba962f).
Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #116      +/-   ##
==========================================
- Coverage   96.67%   96.62%   -0.06%     
==========================================
  Files          33       33              
  Lines         661      651      -10     
==========================================
- Hits          639      629      -10     
  Misses         22       22              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.