# Haunted House: A text-based game for comparing the flexibility of mental models in humans and LLMs

arXiv: https://arxiv.org/abs/2503.16437 · HTML: https://mlsanity.com/paper/2503.16437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 7 of 7)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://mlsanity.com/paper/2411.04872/) (2024)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)

## Abstract (arXiv)

This study introduces "Haunted House" a novel text-based game designed to compare the performance of humans and large language models (LLMs) in model-based reasoning. Players must escape from a house containing nine rooms in a 3x3 grid layout while avoiding the ghost. They are guided by verbal clues that they get each time they move. In Study 1, the results from 98 human participants revealed a success rate of 31.6%, significantly outperforming seven state-of-the-art LLMs tested. Out of 140 attempts across seven LLMs, only one attempt resulted in a pass by Claude 3 Opus. Preliminary results suggested that GPT o3-mini-high performance might be higher, but not at the human level. Further analysis of 29 human participants' moves in Study 2 indicated that LLMs frequently struggled with random and illogical moves, while humans exhibited such errors less frequently. Our findings suggest that current LLMs encounter difficulties in tasks that demand active model-based reasoning, offering inspiration for future benchmarks.