Table 2.

Readability and Reliability of the Responses of Large Language Models

Model	Prompts	Readability			Suitability
		Flesch reading ease score	Flesch–Kincaid grade level	Coleman–Liau index	DISCERN score
ChatGPT (Open AI)	Correcting internal valve dysfunction	42.98	9.56	15	42
	Correcting external valve collapse	41.43	9.69	16	42
	Correcting caudal septal dislocation	33.97	10.59	6	44
	Managing turbinate hypertrophy	13.27	13.62	12	41
	Managing tip support after submucous resection	49.02	8.46	18	43
	When to do nasal bone fractures in rhinoplasty	45.42	8.99	12.17	41
Mean (SD)		37.68 (±12.96)	10.15 (±1.84)	12.00 (5.10)	42.17 (±1.17)
Google's BARD	Correcting internal valve dysfunction	61.26	6.98	10	44
	Correcting external valve collapse	61.63	7.25	9	47
	Correcting caudal septal dislocation	36.08	11.27	13	42
	Managing turbinate hypertrophy	23.03	15.2	14	48
	Managing tip support after submucous resection	54.89	8.15	9	47
	When to do nasal bone fractures in rhinoplasty	47.91	9.4	10	50
Mean (SD)		47.47 (±15.32)	9.71 (±3.12)	10.83 (±2.14)	46.33 (±2.88)
Bing AI(Microsoft)	Correcting internal valve dysfunction	25.95	20	16	39
	Correcting external valve collapse	10.17	20.86	14	30
	Correcting caudal septal dislocation	14.41	19.2	14	36
	Managing turbinate hypertrophy	4.89	18.37	19	38
	Managing tip support after submucous resection	NA	25.34	14	NA
	When to do nasal bone fractures in rhinoplasty	36.03	13.56	12	46
Mean (SD)		18.29 (±12.59)	18.25 (±4.84)	12.00 (5.10)	35.75 (±4.03)

NA, not applicable; SD, standard deviation.