A smartphone-sized deep learning model developed by researchers at Université de Montréal distinguished painful from pain-free cats with 95.5% accuracy, using the Feline Grimace Scale, a 2019 tool scoring five facial action units. A 2025 Scientific Reports study found ChatGPT, Gemini, Claude and Perplexity all scored cat pain lower than a veterinary expert, with mostly poor agreement. The article also outlines how owners can apply the scale at home, where a total of 4 or more suggests pain.
No score is assigned. Sources and their independence are shown in the citation chain below.