Back to today’s briefing

Story perspectives

Study Reveals ChatGPT Outperforms Gemini in Medical Diagnostics

2/17/2025

28 3

Summary

Story summary

A recent study reveals alarming findings about AI's cognitive abilities in medical diagnostics. Researchers assessed chatbots, including ChatGPT and Gemini, using the Montreal Cognitive Assessment. ChatGPT-4 achieved a score of 26, reflecting normal function, while the older Gemini 1.0 lagged behind with a score of just 16, raising serious concerns about its reliability in clinical environments.

1 of 1

Story summary

A recent study reveals alarming findings about AI's cognitive abilities in medical diagnostics. Researchers assessed chatbots, including ChatGPT and Gemini, using the Montreal Cognitive Assessment. ChatGPT-4 achieved a score of 26, reflecting normal function, while the older Gemini 1.0 lagged behind with a score of just 16, raising serious concerns about its reliability in clinical environments.