Scripts to reproduce tables from paper

Hello! I recently read your paper and I also have an interest in efficient implementations of rating systems. I'm wondering if you can share the scripts available to reproduce table 1 comparing evalica to the ChatBot Arena implementation? I did some work earlier this year upgrading their system from the logistic regression version to a more optimized version and I'm curious to benchmark my version under the same conditions as evalica. My PR for chatbot arena for reference https://github.com/lm-sys/FastChat/pull/3523