{"id":"W4400009090","doi":"10.20944/preprints202406.1635.v1","title":"Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"SWORD; Computer science; Linguistics; Artificial intelligence; Natural language processing; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003314632,0.0003304074,0.0003990447,0.0002478739,0.000173393,0.0001534218,0.00124046,0.0001681928,0.00004146526],"category_scores_gemma":[0.0005555921,0.0002536441,0.0001528229,0.0003613265,0.00005934862,0.0001060272,0.006161226,0.0009049457,0.0004705754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001476011,"about_ca_system_score_gemma":0.0002391869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007294113,"about_ca_topic_score_gemma":0.00001645418,"domain_scores_codex":[0.9961832,0.0005121534,0.0006319203,0.001223345,0.001103697,0.0003456737],"domain_scores_gemma":[0.9971861,0.0001837005,0.0003735974,0.00134673,0.0008093743,0.0001005195],"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":[0.00005590457,0.0004447048,0.09911665,0.00306337,0.0007457325,0.0001145508,0.1887901,0.1737996,0.1029949,0.06820709,0.0003119489,0.3623555],"study_design_scores_gemma":[0.0006800306,0.0001979153,0.3239281,0.005546739,0.0003081562,0.00009219854,0.003979359,0.5418704,0.09730688,0.01180287,0.01284301,0.001444252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9776555,0.001020896,0.01443816,0.001024236,0.001697334,0.001753219,0.000006953892,0.0001870204,0.002216697],"genre_scores_gemma":[0.9927878,0.00001199966,0.005166331,0.0000729791,0.0002787943,0.0001400372,0.00000380985,0.00002716928,0.001511114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3680708,"threshold_uncertainty_score":0.9999916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.113106583943814,"score_gpt":0.3937495198749102,"score_spread":0.2806429359310962,"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."}}