Table 2. Percent correct and mean difference between ChatGPT and medical trainees.
| Group A |
Average % Correct | Group B | Average % Correct | Mean Difference (A-B) | Sig. | 95% Confidence Interval | |
|---|---|---|---|---|---|---|---|
| Lower Bound | Upper Bound | ||||||
| ChatGPT | 54.66 | MS1 | 28.75 | 25.91* | < .001 | 8.40 | 43.43 |
| MS2 | 31.44 | 23.22* | .003 | 5.22 | 41.21 | ||
| MS3 | 36.00 | 18.66* | .019 | 1.83 | 35.49 | ||
| MS4 | 37.77 | 16.89 | .104 | -1.72 | 35.50 | ||
| PGY-1 | 49.18 | 5.49 | .996 | -15.13 | 26.10 | ||
| PGY-2 | 56.68 | -2.01 | 1.000 | -22.63 | 18.60 | ||
| PGY-3 | 70.83 | -16.17 | .242 | -36.78 | 4.45 | ||
| PGY-4 | 81.65 | -26.99* | .033 | -52.70 | -1.28 | ||
| PGY-5 | 84.47 | -29.81* | .002 | -52.25 | -7.36 | ||
| MS–Medical Student Year, PGY–Post graduate year | |||||||