SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors

TL;DR

SimBench provides a standardized benchmark to evaluate how well large language models simulate human behaviors across diverse tasks, revealing current limitations and guiding future improvements.

Contribution

Introduces SimBench, the first large-scale, unified benchmark for assessing LLMs' fidelity in simulating human behaviors across multiple datasets.

Findings

Current LLMs achieve modest simulation fidelity (score: 40.80/100).

Performance scales with model size but not inference compute.

Simulation ability correlates strongly with knowledge-intensive reasoning (r = 0.939).

Abstract

Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human behaviors. Current evaluations of simulation fidelity are fragmented, based on bespoke tasks and metrics, creating a patchwork of incomparable results. To address this, we introduce SimBench, the first large-scale, standardized benchmark for a robust, reproducible science of LLM simulation. By unifying 20 diverse datasets covering tasks from moral decision-making to economic choice across a large global participant pool, SimBench provides the necessary foundation to ask fundamental questions about when, how, and why LLM simulations succeed or fail. We show that the best LLMs today achieve meaningful but modest simulation fidelity (score: 40.80/100), with performance scaling log-linearly with model size but not with increased inference-time compute. We discover an alignment-simulation tradeoff: instruction tuning improves performance on low-entropy (consensus) questions but degrades it on high-entropy (diverse) ones. Models particularly struggle when simulating specific demographic groups. Finally, we demonstrate that simulation ability correlates most strongly with knowledge-intensive reasoning (MMLU-Pro, r = 0.939). By making progress measurable, we aim to accelerate the development of more faithful LLM simulators.