{"id":"W4402193259","doi":"10.3390/app14177782","title":"Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"SWORD; Linguistics; Psychology; Computer science; Philosophy; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001570704,0.00006299755,0.00009518422,0.0001135836,0.0001997911,0.00005044591,0.00008926028,0.00003035309,0.0000463699],"category_scores_gemma":[0.0001846489,0.00003821723,0.00001829899,0.0006650473,0.0002046251,0.00005921739,0.00003291657,0.00008502927,0.0000451335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003016043,"about_ca_system_score_gemma":0.0002738115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004017902,"about_ca_topic_score_gemma":0.00006101042,"domain_scores_codex":[0.9988038,0.00003561217,0.000215716,0.0002541858,0.0005384908,0.0001522068],"domain_scores_gemma":[0.9993765,0.0002257626,0.00003826902,0.0001207029,0.000180901,0.00005788117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001230235,0.00003489053,0.00120763,0.00008757442,0.000005825294,0.000001039019,0.02243699,0.0002801228,0.03364387,0.00227365,0.0005634505,0.9394526],"study_design_scores_gemma":[0.0002115115,0.001462593,0.05566506,0.001079534,0.0003266179,0.00009553387,0.2024197,0.3420271,0.3713903,0.01935177,0.005503101,0.0004670491],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891586,0.001050355,0.0002847936,0.005644908,0.0002992698,0.0007981515,0.00000123813,0.00002712714,0.002735552],"genre_scores_gemma":[0.996821,0.00001273399,0.002519273,0.0003836375,0.0001686922,0.00004597738,0.000002036592,0.000003918859,0.00004266333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9389856,"threshold_uncertainty_score":0.1558453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1488573738870522,"score_gpt":0.4834961722266035,"score_spread":0.3346387983395512,"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."}}