CAREB: Chemical Accuracy Reaction Energy Dataset and Benchmark for Neural Density Functionals

We introduce the largest openly available dataset for neural density functional theory, coupling 130 053 highly accurate reaction-energy targets to a unified reaction representation with DFT-level features for every molecular state. The dataset compiles and standardizes decades of DFA benchmarking across thermochemistry, kinetics, noncovalent interactions, barrier heights, atomization reactions, and DES15K dimer profiles, and is designed to support development of accurate DFT methods including neural functionals and ML $\Delta$-learning on top of DFA baselines. In this work, we instantiate this setting by finetuning the Skala neural XC functional and training $\Delta$-learning models in our benchmark, establishing strong baselines and highlighting chemical regimes where neural DFT still falls short of high-level accuracy. Additionally, a small representative subset of Gold Standard Chemistry Database was constructed by an evolutionary algorithm allowing model selection to be accelerated by orders of magnitude. By releasing all reference data, DFT-derived inputs, training code, and pretrained models, our work opens the way to fully reproducible development and systematic stress-testing of neural DFT architectures.