This page accompanies the paper published in Nature Computational Science.
https://www.nature.com/articles/s43588-023-00527-x
See [FAQ][1] for more info.
In the files section you will find:
1. human_responses.xlsx: Responses of human raters collected on prolific.co
2. human_responses.R: R code used to compute human performance
3. LLMs_responses.py: Python code used to query OpenAI API to get LLMs responses. It also includes all of the tasks.
[1]: https://osf.io/w5vhp/wiki/Frequently%20Asked%20Questions/