{"id":"W4416800171","doi":"10.1109/snpd65828.2025.11254480","title":"Benchmarking Large Language Models: A Comparative Study of DeepSeek and ChatGPT Across Diverse Domains","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Relevance (law); Generative grammar; Likert scale; Key (lock); Generative model; Variation (astronomy); Core (optical fiber)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01329471,0.0008466456,0.0007798775,0.001123201,0.0004083994,0.00196879,0.001239423,0.0009723355,0.001473995],"category_scores_gemma":[0.07832567,0.0003210574,0.000509897,0.001031016,0.0007286328,0.00271598,0.002375741,0.001333658,0.001116735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008743356,"about_ca_system_score_gemma":0.001123668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00209033,"about_ca_topic_score_gemma":0.002945289,"domain_scores_codex":[0.9878551,0.008510545,0.0007706512,0.0009983615,0.001567591,0.0002976763],"domain_scores_gemma":[0.9055961,0.0792099,0.002273502,0.00569782,0.005576871,0.001645828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007958793,0.00534929,0.1316064,0.004756092,0.000578464,0.001502147,0.03497496,0.1143582,0.03828757,0.004707007,0.01710379,0.6388174],"study_design_scores_gemma":[0.00124889,0.0163496,0.1550047,0.001046417,0.000548406,0.002289473,0.02232348,0.6520088,0.06721456,0.01501742,0.06623417,0.0007141365],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554187,0.0004165991,0.03371098,0.0003446408,0.00007860962,0.0004941258,0.001149892,0.004944819,0.003441597],"genre_scores_gemma":[0.9510368,0.0002508103,0.04230891,0.0002253717,0.00002775032,0.0004270465,0.003532645,0.0008238769,0.001366832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01329471,"threshold_uncertainty_score":0.07031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1707211146994358,"score_gpt":0.4825841860854528,"score_spread":0.311863071386017,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}