CausalBench+

CausalBench+

CausalBench+ is a transparent, fair, and easy-to-use benchmarking platform for machine learning and causal learning, designed to (a) accelerate research by facilitating open scientific collaboration on new algorithms, datasets, and metrics, and (b) promote scientific objectivity, reproducibility, fairness, and bias awareness in empirical evaluation. CausalBench provides services for downloading and exploring benchmarking data, tasks, models, metrics, and benchmark results—supporting both general ML benchmarks and causality-focused evaluations.

GitHub
🎉 We've Hit 1,000+ Datasets!
MILESTONE

Sign In

Enter your credentials to access your account

Don't have an account?
This work is supported by NSF grant 2311716, CausalBench: A Cyberinfrastructure for Causal-Learning Benchmarking for Efficacy, Reproducibility, and Scientific Collaboration