The primary challenge for practitioners with multiple post-hoc gradient-based interpretability methods is to benchmark them and select the best. Using information theory, we represent finding the optimal explainer as a rate-distortion optimization problem. Therefore : * We propose an information-theoretic test to resolve the benchmarking ambiguity in a model agnostic manner without additional user data (apart from the input features, model, and explanations). * We show that is extendable to util…