# Working Memory Capacity of ChatGPT: An Empirical Study

arXiv: https://arxiv.org/abs/2305.03731 · HTML: https://mlsanity.com/paper/2305.03731/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 30 Apr 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [Large Language Models with Controllable Working Memory](https://mlsanity.com/paper/2211.05110/) (2022)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [The Turking Test: Can Language Models Understand Instructions?](https://mlsanity.com/paper/2010.11982/) (2020)

## Built on by (most cited first, 23 of 23)

- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Understanding the Dark Side of LLMs' Intrinsic Self-Correction](https://mlsanity.com/paper/2412.14959/) (2024)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [An In-depth Survey of Large Language Model-based Artificial Intelligence Agents](https://mlsanity.com/paper/2309.14365/) (2023)
- [Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding](https://mlsanity.com/paper/2502.06020/) (2025)
- [Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length](https://mlsanity.com/paper/2506.08184/) (2025)
- [Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests](https://mlsanity.com/paper/2502.14359/) (2025)
- [United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory](https://mlsanity.com/paper/2506.06843/) (2025)
- [On the Failure of Latent State Persistence in Large Language Models](https://mlsanity.com/paper/2505.10571/) (2025)
- [GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding](https://mlsanity.com/paper/2508.12379/) (2025)
- [Towards Building Specialized Generalist AI with System 1 and System 2 Fusion](https://mlsanity.com/paper/2407.08642/) (2024)
- [Whither symbols in the era of advanced neural networks?](https://mlsanity.com/paper/2508.05776/) (2025)
- [Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs](https://mlsanity.com/paper/2504.02789/) (2025)
- [Self-Attention Limits Working Memory Capacity of Transformer-Based Models](https://mlsanity.com/paper/2409.10715/) (2024)
- [CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants](https://mlsanity.com/paper/2410.21159/) (2024)
- [A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities](https://mlsanity.com/paper/2603.02540/) (2026)
- [Evaluating Cognitive Age Alignment in Interactive AI Agents](https://mlsanity.com/paper/2605.17894/) (2026)
- [M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks](https://mlsanity.com/paper/2606.05008/) (2026)
- [Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm](https://mlsanity.com/paper/2412.18120/) (2024)
- [In-context superposition: human-like working memory interference in large language models](https://mlsanity.com/paper/2604.09670/) (2026)
- [Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets](https://mlsanity.com/paper/2609.29509/) (2026)
- [A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models](https://mlsanity.com/paper/2604.26351/) (2026)
- [In-Context Binding Capacity in Language Models](https://mlsanity.com/paper/2609.30634/) (2026)

## Abstract (arXiv)

Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In this paper, we systematically assess the working memory capacity of ChatGPT, a large language model developed by OpenAI, by examining its performance in verbal and spatial n-back tasks under various conditions. Our experiments reveal that ChatGPT has a working memory capacity limit strikingly similar to that of humans. Furthermore, we investigate the impact of different instruction strategies on ChatGPT's performance and observe that the fundamental patterns of a capacity limit persist. From our empirical findings, we propose that n-back tasks may serve as tools for benchmarking the working memory capacity of large language models and hold potential for informing future efforts aimed at enhancing AI working memory.