# SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models

arXiv: https://arxiv.org/abs/2510.11131 · HTML: https://mlsanity.com/paper/2510.11131/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2025.

## Built on by (most cited first, 5 of 5)

- [When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses](https://mlsanity.com/paper/2607.26348/) (2026)
- [From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes](https://mlsanity.com/paper/2605.16303/) (2026)
- [BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks](https://mlsanity.com/paper/2606.24162/) (2026)
- [Rethinking the Evaluation and Optimization of LLM-Based Social Simulation](https://mlsanity.com/paper/2608.19689/) (2026)
- [Artificial Societies Benchmark: A Validation Framework for Synthetic Research](https://mlsanity.com/paper/2609.30030/) (2026)

## Abstract (arXiv)

Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes. To bridge this gap, we introduce SocioBench-a comprehensive benchmark derived from the annually collected, standardized survey data of the International Social Survey Programme (ISSP). The benchmark aggregates over 480,000 real respondent records from more than 30 countries, spanning 10 sociological domains and over 40 demographic attributes. Our experiments indicate that LLMs achieve only 30-40% accuracy when simulating individuals in complex survey scenarios, with statistically significant differences across domains and demographic subgroups. These findings highlight several limitations of current LLMs in survey scenarios, including insufficient individual-level data coverage, inadequate scenario diversity, and missing group-level modeling.