Table 3 Comparison of human performance and o1-preview model performance on the EWCTET.
From: Comparative evaluation of OpenAI O1 and human performance in higher order cognition
Participant category | Mean total score | o1-Preview mean score | Z-score |
|---|---|---|---|
Undergraduate students (highest after treatment) | 13.8 | 24.33 | 1.60 |
Postgraduate students | 18.39 | 24.33 | 0.90 |
