# GPT-4 solved three quarters of a false-belief test battery

> A demanding all-or-nothing score across 40 bespoke tasks produced a wide gap between older systems and the June 2023 GPT-4.

Canonical: https://aischolar.cc/blog/false-belief-theory-of-mind

[← All articles](https://aischolar.cc/blog)

AISCHOLAR / BLOG

# GPT-4 solved three quarters of a false-belief test battery

A demanding all-or-nothing score across 40 bespoke tasks produced a wide gap between older systems and the June 2023 GPT-4.

November 4, 2026

### A model had to pass every version of a story

Michal Kosinski evaluated eleven language models on 40 false-belief tasks in [_Evaluating Large Language Models in Theory of Mind Tasks_](https://arxiv.org/pdf/2302.02083). Each task paired a false-belief scenario with three matched true-belief controls, then reversed the versions. The model received a point only if it answered all eight scenarios correctly.

Older models in the study solved no tasks; GPT-3-davinci-003 and ChatGPT-3.5-turbo solved 20%, while the June 2023 GPT-4 solved 75%. The paper compares GPT-4’s score with a historical average reported for six-year-old children on prior false-belief studies. That is a benchmark comparison, not a claim that the systems share a developmental or cognitive ability.

The task battery gives a clear way to test whether answers follow who has seen what. Its scripted stories also leave other demands in play: the paper notes that vocabulary, commonsense assumptions, item wording, procedure, and scoring can affect performance. Future task sets can vary those features to identify which story elements drive success or failure.

### Bibliography

-   Kosinski, M. (2023). _Evaluating Large Language Models in Theory of Mind Tasks_. arXiv:2302.02083v7 \[cs.CL\]. [Full paper (PDF)](https://arxiv.org/pdf/2302.02083).

Original source: [https://arxiv.org/pdf/2302.02083](https://arxiv.org/pdf/2302.02083)

About AIScholar

## Study LLM behavior.

AIScholar is a research workspace for controlled, replicated studies of LLM behavior using single-turn text responses from OpenRouter-served models. The nine-stage workflow includes response coding, visualization, analysis and write-up; researchers validate measurements and interpret results.

[Explore AIScholar ↗](https://aischolar.cc/features)
