Table 3.
Relative and standardized scores of answers provided by experts and ChatGPT.
| Internal medicine | |||||
|---|---|---|---|---|---|
| Benchmark | |||||
| Compre. | Accu. | Compre. | Accu. | Final | |
| 1 | 5 | 5 | 1 | 1 | 1 |
| 2 | 4 | 4 | 1 | 1 | 1 |
| 3 | 4 | 4 | 1 | 1 | 1 |
| 4 | 3 | 3 | 1 | 1 | 1 |
| 5 | 4 | 4 | 1 | 1 | 1 |
| 6 | 4 | 4 | 1 | 1 | 1 |
| 7 | 5 | 5 | 1 | 1 | 1 |
| 8 | 7 | 7 | 1 | 1 | 1 |
| 9 | 6 | 6 | 1 | 1 | 1 |
| 10 | 8 | 8 | 1 | 1 | 1 |
| 11 | 4 | 4 | 1 | 1 | 1 |
| 12 | 5 | 5 | 1 | 1 | 1 |
| 13 | 3 | 3 | 1 | 1 | 1 |
| 14 | 4 | 4 | 1 | 1 | 1 |
| 15 | 5 | 5 | 1 | 1 | 1 |
| 16 | 7 | 7 | 1 | 1 | 1 |
| 17 | Repeated | ||||
| 18 | 5 | 5 | 1 | 1 | 1 |
| 19 | 4 | 4 | 1 | 1 | 1 |
| 20 | 3 | 3 | 1 | 1 | 1 |
| 21 | 3 | 3 | 1 | 1 | 1 |
| 22 | 2 | 2 | 1 | 1 | 1 |
| 23 | 4 | 4 | 1 | 1 | 1 |
| 24 | 4 | 4 | 1 | 1 | 1 |
| 25 | 4 | 4 | 1 | 1 | 1 |
| 26 | 2 | 2 | 1 | 1 | 1 |
| 27 | 4 | 4 | 1 | 1 | 1 |
| 28 | 7 | 7 | 1 | 1 | 1 |
| 29 | 5 | 5 | 1 | 1 | 1 |
| 30 | 2 | 2 | 1 | 1 | 1 |
| 31 | 2 | 2 | 1 | 1 | 1 |
| 32 | 4 | 4 | 1 | 1 | 1 |
| 33 | 4 | 4 | 1 | 1 | 1 |
| 34 | 3 | 3 | 1 | 1 | 1 |
| 35 | 5 | 5 | 1 | 1 | 1 |
| ChatGPT | |||||
|---|---|---|---|---|---|
| Compre. | Accu. | Compre. | Accu. | Final | |
| 1 | 4 | 5 | 0.8 | 1 | 0.9 |
| 2 | 1 | 4 | 0.25 | 1 | 0.625 |
| 3 | 4 | 4 | 1 | 1 | 1 |
| 4 | 3 | 3 | 1 | 1 | 1 |
| 5 | 3 | 4 | 0.75 | 1 | 0.875 |
| 6 | 4 | 4 | 1 | 1 | 1 |
| 7 | 3 | 4 | 0.6 | 0.8 | 0.7 |
| 8 | 5 | 7 | 0.71428571 | 1 | 0.85714286 |
| 9 | 4 | 6 | 0.66666667 | 1 | 0.83333333 |
| 10 | 4 | 8 | 0.5 | 1 | 0.75 |
| 11 | 3 | 4 | 0.75 | 1 | 0.875 |
| 12 | 4 | 5 | 0.8 | 1 | 0.9 |
| 13 | 3 | 3 | 1 | 1 | 1 |
| 14 | 4 | 4 | 1 | 1 | 1 |
| 15 | 3 | 5 | 0.6 | 1 | 0.8 |
| 16 | 5 | 7 | 0.71428571 | 1 | 0.85714286 |
| 17 | |||||
| 18 | 4 | 5 | 0.8 | 1 | 0.9 |
| 19 | 2 | 3 | 0.5 | 0.75 | 0.625 |
| 20 | 2 | 2 | 0.66666667 | 0.66666667 | 0.66666667 |
| 21 | 1 | 2 | 0.33333333 | 0.66666667 | 0.5 |
| 22 | 2 | 2 | 1 | 1 | 1 |
| 23 | 2 | 4 | 0.5 | 1 | 0.75 |
| 24 | 3 | 4 | 0.75 | 1 | 0.875 |
| 25 | 4 | 4 | 1 | 1 | 1 |
| 26 | 2 | 2 | 1 | 1 | 1 |
| 27 | 4 | 4 | 1 | 1 | 1 |
| 28 | 3 | 7 | 0.42857143 | 1 | 0.71428571 |
| 29 | 4 | 5 | 0.8 | 1 | 0.9 |
| 30 | 2 | 2 | 1 | 1 | 1 |
| 31 | 2 | 2 | 1 | 1 | 1 |
| 32 | 3 | 4 | 0.75 | 1 | 0.875 |
| 33 | 2 | 4 | 0.5 | 1 | 0.75 |
| 34 | 3 | 3 | 1 | 1 | 1 |
| 35 | 4 | 5 | 0.8 | 1 | 0.9 |
| ChatGPT Rep2 | |||||
|---|---|---|---|---|---|
| Compre. | Accu. | Compre. | Accu. | Final | |
| 1 | 4 | 5 | 0.8 | 1 | 0.9 |
| 2 | 1 | 4 | 0.25 | 1 | 0.625 |
| 3 | 4 | 4 | 1 | 1 | 1 |
| 4 | 3 | 3 | 1 | 1 | 1 |
| 5 | 3 | 4 | 0.75 | 1 | 0.875 |
| 6 | 4 | 4 | 1 | 1 | 1 |
| 7 | 2 | 4 | 0.4 | 0.8 | 0.6 |
| 8 | 4 | 7 | 0.57142857 | 1 | 0.78571429 |
| 9 | 4 | 6 | 0.66666667 | 1 | 0.83333333 |
| 10 | 4 | 6 | 0.5 | 0.75 | 0.625 |
| 11 | 3 | 4 | 0.75 | 1 | 0.875 |
| 12 | 4 | 5 | 0.8 | 1 | 0.9 |
| 13 | 3 | 3 | 1 | 1 | 1 |
| 14 | 3 | 4 | 0.75 | 1 | 0.875 |
| 15 | 4 | 5 | 0.8 | 1 | 0.9 |
| 16 | 5 | 7 | 0.71428571 | 1 | 0.85714286 |
| 17 | |||||
| 18 | 1 | 2 | 0.2 | 0.4 | 0.3 |
| 19 | 1 | 3 | 0.25 | 0.75 | 0.5 |
| 20 | 2 | 3 | 0.66666667 | 1 | 0.83333333 |
| 21 | 1 | 0 | 0.33333333 | 0 | 0.16666667 |
| 22 | 2 | 2 | 1 | 1 | 1 |
| 23 | 2 | 4 | 0.5 | 1 | 0.75 |
| 24 | 3 | 4 | 0.75 | 1 | 0.875 |
| 25 | 4 | 4 | 1 | 1 | 1 |
| 26 | 2 | 2 | 1 | 1 | 1 |
| 27 | 4 | 4 | 1 | 1 | 1 |
| 28 | 3 | 7 | 0.42857143 | 1 | 0.71428571 |
| 29 | 4 | 5 | 0.8 | 1 | 0.9 |
| 30 | 2 | 2 | 1 | 1 | 1 |
| 31 | 2 | 2 | 1 | 1 | 1 |
| 32 | 3 | 4 | 0.75 | 1 | 0.875 |
| 33 | 2 | 4 | 0.5 | 1 | 0.75 |
| 34 | 3 | 3 | 1 | 1 | 1 |
| 35 | 3 | 5 | 0.6 | 1 | 0.8 |
*Compre. (Comprehensiveness of Information).
#Accu. (Accuracy of Information).