The study claims o1-preview surpasses human averages on several higher-order thinking tests, but post-hoc benchmark choices, missing statistics, and unaddressed training-data contamination make the claim unreliable.
Can generative AI and ChatGPT outperform humans on cognitive-demanding problem-solving tasks in science? Science & Education
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CY 1years
2024 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Can OpenAI o1 outperform humans in higher-order cognitive thinking?
The study claims o1-preview surpasses human averages on several higher-order thinking tests, but post-hoc benchmark choices, missing statistics, and unaddressed training-data contamination make the claim unreliable.