{"id":"W4412791697","doi":"10.2196/76925","title":"Performance Evaluation of 18 Generative AI Models (ChatGPT, Gemini, Claude, and Perplexity) in 2024 Japanese Pharmacist Licensing Examination: Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perplexity; Preprint; Generative grammar; Psychology; Medicine; Computer science; Artificial intelligence; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001806893,0.0001453063,0.000310483,0.0004230043,0.0001087677,0.00002084642,0.00007473005,0.0001363742,0.0003824065],"category_scores_gemma":[0.0004957011,0.0001357075,0.00002736866,0.0007734304,0.0001620299,0.0002943824,0.00002904389,0.0003538606,0.000008625348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003544661,"about_ca_system_score_gemma":0.002908963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000365675,"about_ca_topic_score_gemma":0.0002487662,"domain_scores_codex":[0.9976885,0.0003670617,0.0006504636,0.00034133,0.0007797311,0.0001728884],"domain_scores_gemma":[0.9982633,0.000163444,0.0001393058,0.0002043104,0.001074658,0.0001550076],"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":[0.0003920688,0.005809146,0.1275981,0.0005629207,0.00008479015,0.000001866622,0.2050712,0.0003124121,0.0003984443,0.0004762404,0.005053691,0.6542392],"study_design_scores_gemma":[0.0008608429,0.0005192584,0.2189394,0.001129677,0.0002099677,0.00001622133,0.09320667,0.6810698,0.002648233,0.0009094226,0.0002792988,0.0002112324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872534,0.000601418,0.00006017398,0.002679612,0.0008493636,0.001906735,0.000001031272,0.0000154661,0.006632779],"genre_scores_gemma":[0.9973263,0.0001290019,0.0001097974,0.0009175361,0.000265446,0.0004916858,0.0000473708,0.000007564324,0.0007053106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6807573,"threshold_uncertainty_score":0.5533989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2598460124644382,"score_gpt":0.5373930788811854,"score_spread":0.2775470664167472,"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."}}