Skip to main content
. 2024 Jul 19;7:193. doi: 10.1038/s41746-024-01181-x

Fig. 1. Diagnostic accuracy of LLMs by case (OCD) and control (other psychiatric disorders).

Fig. 1

Overall LLM performance: Case (N = 49/51) and control (N = 21/21). ChatGPT-4 and Gemini Pro (Case: 16 OCD vignettes) and Llama 3 (Case: 19 OCD vignettes). All LLMs had the same control group comprised of seven psychiatric disorders (major depressive disorder, generalized anxiety disorder, post-traumatic stress disorder, uni or bipolar depression, depression among adolescents, social anxiety disorder, and panic disorder).