A peer-reviewed Scientific Reports study published October 8, 2026, found that ChatGPT-5.5 and Gemini 3.1 each answered 82% of a 50-question Persian pharmacology test correctly, while Claude 4.6 scored 72%. The comparison used the same multiple-choice questionnaire for all three models.
What the study found
The open-access paper reports sensitivity of 1.00 for ChatGPT-5.5, 0.94 for Gemini 3.1 and 0.90 for Claude 4.6. Gemini posted the highest specificity at 0.50, compared with 0.43 for ChatGPT and 0.35 for Claude. Across all three models, mean accuracy was 78%.
ChatGPT-5.5 and Gemini 3.1 therefore tied on overall accuracy but differed in how they reached that result: ChatGPT had the strongest sensitivity, while Gemini had the strongest specificity. The researchers also found a statistically significant performance decline for both ChatGPT-5.5 and Gemini 3.1 on quantitative questions.
What the result does not prove
This was a 50-item educational benchmark conducted in Persian, not a clinical-outcomes trial, diagnosis study or test of patient-care decisions. The authors concluded that large language models may be useful in pharmacology education and knowledge work but said more research is needed to understand their limitations. They reported no competing interests.
Competitive context
The study adds a narrow medical-education comparison to a rapidly changing model race. BitcoinVersus.Tech recently covered Google Cloud’s Gemini Agent push, Arm’s latest comparative AI-infrastructure benchmark, and the broader debate around AI training and labor.
BitcoinVersus.Tech is not a financial advisor. This media platform reports on financial subjects purely for informational purposes.
BitcoinVersus.Tech Editor’s Note:
We volunteer daily to ensure the credibility of the information on this platform is Verifiably True. If you would like to support to help further secure the integrity of our research initiatives, please donate using the QR code provided
For best QR-code scanning results, please scan this donation code from a desktop or larger screen. Mobile screens may prevent camera recognition.
Leave a Reply