DeCoDE Lab
MIT

CarBench

CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics

Mohamed Elrefaie1, 2, Dule Shu3, Matt Klenk3, Faez Ahmed1, 2

1Department of Mechanical Engineering, MIT  2Schwarzman College of Computing, MIT  3Toyota Research Institute 

Explore

CarBench is the first comprehensive benchmark dedicated to large-scale 3D car aerodynamics. It evaluates state-of-the-art deep learning models on DrivAerNet++, the largest public dataset for automotive aerodynamics containing over 8,000 high-fidelity CFD simulations.