Evaluate package performance on classical Tasks

[micedre]

We should benchmark the package on some classic tasks to compare to others, both on accuracy and inference time.

For exemple, this article :
Reusens, M., Stevens, A., Tonglet, J., De Smedt, J., Verbeke, W., Vanden Broucke, S., & Baesens, B. (2024). Evaluating Text Classification: A Benchmark Study. In Expert Systems With Applications (Vol. 254). Elsevier. https://doi.org/10.1016/j.eswa.2024.124302