Table 2.
Total and subgroup scores of the best attempt of each chatbot
| GPT-4 | Bing | Claude | Bard | GPT-3 | Total | |
|---|---|---|---|---|---|---|
| Total | 157 (87.2) | 152 (84.4) | 129 (71.6) | 124 (68.8) | 124 (68.8) | 180 |
| Area | ||||||
| Surgery | 26 (96.2) | 22 (81.48) | 17 (62.9) | 20 (74.07) | 19 (70.3) | 27 |
| Internal medicine | 68 (90) | 68 (90) | 59 (78.6) | 52 (69.3) | 55 (73.3) | 75 |
| Pediatrics | 14 (77.7) | 11 (61.1) | 11 (61.1) | 11 (61.1) | 10 (55.5) | 18 |
| Obstetrics & gynecology | 24 (68.5) | 27 (77.1) | 17 (48.5) | 17 (48.5) | 21 (60) | 35 |
| Public health | 18 (85.7) | 16 (76) | 18 (85.7) | 17 (80.9) | 15 (71.4) | 21 |
| Emergency medicine | 7 (87.5) | 8 (100) | 7 (87.5) | 7 (87.5) | 4 (50) | 8 |
| Peruvian knowledge | ||||||
| Required | 24 (70.5) | 27 (79.4) | 24 (70.5) | 21 (61.7) | 21 (61.7) | 34 |
| Not required | 133 (91.09) | 125 (85.6) | 105 (71.9) | 103 (70.5) | 103 (70.5) | 146 |
| Type of item | ||||||
| Recall | 30 (78.9) | 32 (84.2) | 30 (78.9) | 31 (81.5) | 27 (71.05) | 38 |
| Application of knowledge | 127 (89.4) | 120 (84.5) | 99 (69.7) | 94 (66.1) | 97 (68.3) | 142 |
Values are presented as number (%) or number.