The classification accuracy results for the 26 UEA multivariate TSC problems presented in the multivariate bake off are available here. This includes additional classifiers from the later released HC2 paper.
There results use tsml where possible. The implementation availability for different languages and open source packages is displayed via table in the paper. For Python implementations we recommend using the ones tested for performance in the aeon Python time series package (a fork of sktime).
Section 4.1 and 4.2 of the bakeoff publication contain basic guidance on running algorithms from these packages. Feel free to contact the authors via email if you need any additional results or guidance.