Evaluating the performance of general purpose large language models in identifying human facial emotions.

ABSTRACT: We evaluated the ability of three leading LLMs (GPT-4o, Gemini 2.0 Experimental, and Claude 3.5 Sonnet) to recognize human facial expression using the NimStim dataset. GPT and Gemini matched or exceeded human performance, especially for calm/neutral and surprise. All models showed strong agreement with ground truth, though fear was often misclassified. Findings underscore the growing socioemotional competence of LLMs and their potential for healthcare applications.

SUBMITTER: Nelson BW 

PROVIDER: S-EPMC12533101 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature