Table 5 Comparison of o1-preview model and human performance on CT skills.
From: Comparative evaluation of OpenAI O1 and human performance in higher order cognition
CT dimension | Human overall | o1-Preview | Z-Score |
|---|---|---|---|
CT skills | 3.92 ± 0.52 | 3.84 ± 1.56 | − 0.15 |
Creativity | 4.18 ± 0.63 | 4.56 ± 0.73 | 0.60 |
Algorithmic thinking | 4.30 ± 0.62 | 4.50 ± 0.67 | 0.32 |
Cooperativity | 3.94 ± 0.78 | 4.50 ± 0.53 | 0.72 |
Critical thinking | 3.93 ± 0.63 | 4.80 ± 0.42 | 1.38 |
Problem-solving | 3.68 ± 0.63 | 1.00 ± 0.00 | − 4.25 |