Table 10.
Mean Scores for Large Language Models’ Responses to Questions About Choice of a Contraceptive Method
| Good (a Mean Score>4) n (%) | Average (3<Mean Score ≤ 4) n (%) | Poor (a Mean Score ≤ 3) n (%) | Total n (%) | |
|---|---|---|---|---|
| ChatGPT 4.0 Turbo | 55 (87.30%) | 8 (12.70%) | 0 (0.00%) | 63 (100%) |
| Kimi 2.1.4 | 57 (90.48%) | 4 (6.35%) | 2 (3.17%) | 63 (100%) |
| Ernie Bot 3.5 | 55 (87.30%) | 8 (12.70%) | 0 (0.00%) | 63 (100%) |