PDEBench and CFDBench
These are complements that address different scopes of the same problem: PDEBench provides a broad benchmark across multiple PDE types including fluid dynamics, while CFDBench specializes in large-scale fluid dynamics benchmarks with potentially deeper domain-specific scenarios, allowing practitioners to validate ML models across both general PDE solving and fluid-specific challenges.
About PDEBench
pdebench/PDEBench
PDEBench: An Extensive Benchmark for Scientific Machine Learning
Encompasses diverse PDE problems (diffusion-reaction, Navier-Stokes, shallow-water, Darcy flow, and others) with forward and inverse problem variants, alongside dataset generation tools using JAX and PyTorch. Provides pre-trained baseline models and integrates with DeepXDE, Hydra configuration management, and HDF5-based datasets hosted on Dataverse for reproducibility and extensibility.
About CFDBench
luo-yining/CFDBench
A large-scale benchmark for machine learning methods in fluid dynamics
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work