{"id":"W4413846962","doi":"10.2196/67661","title":"Rapidly Benchmarking Large Language Models for Diagnosing Comorbid Patients: Comparative Study Leveraging the LLM-as-a-Judge Method","year":2025,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Computer science; Natural language processing; Data science; Artificial intelligence; Psychology; Business","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01414249,0.001848939,0.001270543,0.00306057,0.000582554,0.002083012,0.002519953,0.002384417,0.001455709],"category_scores_gemma":[0.05391141,0.000502972,0.001456455,0.001274957,0.0006928939,0.001957534,0.002120825,0.001714339,0.0009992394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001606148,"about_ca_system_score_gemma":0.001624041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120309,"about_ca_topic_score_gemma":0.01296326,"domain_scores_codex":[0.9892752,0.006647349,0.0008583163,0.001790977,0.0010849,0.0003433363],"domain_scores_gemma":[0.9549922,0.03578616,0.001414507,0.003362962,0.003370437,0.001073633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007384633,0.003851205,0.2130417,0.001438811,0.002420392,0.001351663,0.001245836,0.3476242,0.006157099,0.001872362,0.02593599,0.3876761],"study_design_scores_gemma":[0.0003389197,0.001364322,0.01600444,0.00006859551,0.000221943,0.0003632762,0.0004086076,0.9746991,0.00318305,0.001529893,0.001747358,0.00007062146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379286,0.002694742,0.0430553,0.001307063,0.000420315,0.000697332,0.00437057,0.006737594,0.002788583],"genre_scores_gemma":[0.9316825,0.0003413257,0.05719861,0.0004763792,0.0001433154,0.0002194367,0.009104355,0.0002373826,0.000596847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01414249,"threshold_uncertainty_score":0.07479358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1637073614546578,"score_gpt":0.4996994509340316,"score_spread":0.3359920894793739,"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."}}