2026-10-14T13:58:04Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33866138 2026-09-16T17:36:10Z category_7 category_14 category_61 category_64 category_106 portal_5 item_type_3 month_year_09_2026

<p>Comparison of ChatGPT and Gemini across three evaluation domains: scientific accuracy, clarity, and level of unnecessary detail, for each evaluator (R1–R4) and overall results.</p> Yeliz Yilmaz Bozok (24998657) Nihan Acar (24998660) Murat Kemal Atahan (24998663) Cem Karaali (24998666) Medicine Molecular Biology Developmental Biology Cancer Science Policy turkish online sources overall median score generated health information 08 &# 8211 50 &# 8211 chatgpt &# 8217 focused responses indicate based language models 25 &# 8211 gemini &# 8217 00 &# 8211 related patient questions study compared chatgpt 001 ], clarity 005 ], oriented questions 001 ]. 001 ). xlink "> unnecessary detail significantly longer scientific accuracy response using rapid growth potential roles making purposes identical conditions higher scores expert supervision efficient tool current form comparative evaluation clinical decision breast cancer blinded evaluation august 13 47 words <p>Comparison of ChatGPT and Gemini across three evaluation domains: scientific accuracy, clarity, and level of unnecessary detail, for each evaluator (R1–R4) and overall results.</p> 2026-09-16T17:36:05Z Dataset Dataset 10.1371/journal.pone.0358325.t001 https://figshare.com/articles/dataset/_p_Comparison_of_ChatGPT_and_Gemini_across_three_evaluation_domains_scientific_accuracy_clarity_and_level_of_unnecessary_detail_for_each_evaluator_R1_R4_and_overall_results_p_/33866138 CC BY 4.0