SimBench: A Framework for Evaluating and Diagnosing LLM-Based Digital-Twin Generation for Multi-Physics Simulation

TL;DR

SimBench is a comprehensive benchmark framework that evaluates the ability of simulator-oriented large language models to generate high-quality digital twins for multi-physics simulation, using an LLM-based judging system and multi-physics testing with Chrono.

Contribution

This paper introduces SimBench, a novel benchmarking approach for assessing S-LLMs' digital twin generation capabilities across multiple physics simulators, with an innovative LLM-based evaluation method.

Findings

Over 33 S-LLMs evaluated using SimBench.

J-LLM provides consistent scoring for digital twins.

Framework applicable to various simulation platforms.

Abstract

We introduce SimBench, a benchmark designed to evaluate the proficiency of simulator-oriented LLMs (S-LLMs) in generating digital twins (DTs) that can be used in simulators for virtual testing. Given a collection of S-LLMs, this benchmark ranks them according to their ability to produce high-quality DTs. We demonstrate this by comparing over 33 open- and closed-source S-LLMs. Using multi-turn interactions, SimBench employs an LLM-as-a-judge (J-LLM) that leverages both predefined rules and human-in-the-loop guidance to assign scores for the DTs generated by the S-LLM, thus providing a consistent and expert-inspired evaluation protocol. The J-LLM is specific to a simulator, and herein the proposed benchmarking approach is demonstrated in conjunction with the open-sourceChrono multi-physics simulator. Chrono provided the backdrop used to assess an S-LLM in relation to the latter's ability to create digital twins for multibody dynamics, finite element analysis, vehicle dynamics, robotic dynamics, and sensor simulations. The proposed benchmarking principle is broadly applicable and enables the assessment of an S-LLM's ability to generate digital twins for other simulation packages, e.g., ANSYS, ABAQUS, OpenFOAM, StarCCM+, IsaacSim, and pyBullet.