{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["22(15)"],"submitter":["Li CP"],"pubmed_abstract":["<b>Objective:</b> This study aimed to compare the performance of DeepSeek-R1 and OpenAI-o1 in addressing complex pancreatic ductal adenocarcinoma (PDAC)-related clinical questions, focusing on accuracy, comprehensiveness, safety, and reasoning quality. <b>Methods:</b> Twenty PDAC-related questions derived from the up-to-date NCCN guidelines for PDAC were posed to both models. Responses were evaluated for accuracy, comprehensiveness, and safety, and chain-of-thought (CoT) outputs were rated for logical coherence and error handling by blinded clinical experts using 5-point Likert scales. Inter-rater reliability, evaluated scores, and character counts by both models were compared. <b>Results:</b> Both models demonstrated high accuracy (median score: 5 vs. 5, p=0.527) and safety (5 vs. 5, p=0."],"journal":["International journal of medical sciences"],"pagination":["3868-3877"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12492379"],"repository":["biostudies-literature"],"pubmed_title":["Punching Above Its Weight: A Head-to-Head Comparison of Deepseek-R1 and OpenAI-o1 on Pancreatic Adenocarcinoma-Related Questions."],"pmcid":["PMC12492379"],"pubmed_authors":["Jia WW","Hakenberg P","Reißfelder C","Chu Y","Yang C","Sandra-Petrescu F","Li CP"],"additional_accession":[]},"is_claimable":false,"name":"Punching Above Its Weight: A Head-to-Head Comparison of Deepseek-R1 and OpenAI-o1 on Pancreatic Adenocarcinoma-Related Questions.","description":"<b>Objective:</b> This study aimed to compare the performance of DeepSeek-R1 and OpenAI-o1 in addressing complex pancreatic ductal adenocarcinoma (PDAC)-related clinical questions, focusing on accuracy, comprehensiveness, safety, and reasoning quality. <b>Methods:</b> Twenty PDAC-related questions derived from the up-to-date NCCN guidelines for PDAC were posed to both models. Responses were evaluated for accuracy, comprehensiveness, and safety, and chain-of-thought (CoT) outputs were rated for logical coherence and error handling by blinded clinical experts using 5-point Likert scales. Inter-rater reliability, evaluated scores, and character counts by both models were compared. <b>Results:</b> Both models demonstrated high accuracy (median score: 5 vs. 5, p=0.527) and safety (5 vs. 5, p=0.","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025","modification":"2026-05-05T03:20:32.726Z","creation":"2026-05-05T03:12:54.95Z"},"accession":"S-EPMC12492379","cross_references":{"pubmed":["41049443"],"doi":["10.7150/ijms.118887"]}}