LinearSolveBench is a new benchmark designed to advance algorithms for solving large sparse linear systems and to measure AI models' ability to discover such algorithms. It includes 9,984–113,664 row matrices from FLASH magnetic-diffusion problems and spans applications across power grids, fusion energy, quantitative finance, structural mechanics, and fluid dynamics.
Toymodel is a modular sci-ML framework that uses composable components to build scientific tools without forcing a choice between flexibility and depth. Components can be trained on data while maintaining their interfaces, allowing them to integrate seamlessly with solvers, tables, and charts in a human-inspectable computation environment.