This project aims to create fair benchmarks for performance across (currently 5) different problems, and (currently 4) different types of solvers. The benchmarks are primarily intended to guage the effect of the introduction of a 'TSU' (thermodynamic sampling unit) and what specific challenges it excels in. To run current benchmarks, find the run_benchmarks.py file within the solvers folder, which will benchmark and print results for all of the solver-problem combinations. NOTE: The file will create a new directory to store graph images in upon running.