Index of /helm/benchmark_output/releases/mmlu/groups/json

[ICO]NameLast modifiedSizeDescription

[DIR]Parent Directory  -  
[   ]mmlu_world_religions_mmlu_world_religions_subject:world_religions.json27-Mar-2024 21:39 14K 
[   ]mmlu_virology_mmlu_virology_subject:virology.json27-Mar-2024 21:39 14K 
[   ]mmlu_sociology_mmlu_sociology_subject:sociology.json27-Mar-2024 21:39 14K 
[   ]mmlu_security_studies_mmlu_security_studies_subject:security_studies.json27-Mar-2024 21:39 14K 
[   ]mmlu_public_relations_mmlu_public_relations_subject:public_relations.json27-Mar-2024 21:39 15K 
[   ]mmlu_professional_psychology_mmlu_professional_psychology_subject:professional_psychology.json27-Mar-2024 21:39 15K 
[   ]mmlu_professional_law_mmlu_professional_law_subject:professional_law.json27-Mar-2024 21:39 15K 
[   ]mmlu_professional_accounting_mmlu_professional_accounting_subject:professional_accounting.json27-Mar-2024 21:39 15K 
[   ]mmlu_prehistory_mmlu_prehistory_subject:prehistory.json27-Mar-2024 21:39 14K 
[   ]mmlu_nutrition_mmlu_nutrition_subject:nutrition.json27-Mar-2024 21:39 14K 
[   ]mmlu_moral_scenarios_mmlu_moral_scenarios_subject:moral_scenarios.json27-Mar-2024 21:39 14K 
[   ]mmlu_moral_disputes_mmlu_moral_disputes_subject:moral_disputes.json27-Mar-2024 21:39 14K 
[   ]mmlu_miscellaneous_mmlu_miscellaneous_subject:miscellaneous.json27-Mar-2024 21:39 14K 
[   ]mmlu_medical_genetics_mmlu_medical_genetics_subject:medical_genetics.json27-Mar-2024 21:39 14K 
[   ]mmlu_marketing_mmlu_marketing_subject:marketing.json27-Mar-2024 21:39 14K 
[   ]mmlu_management_mmlu_management_subject:management.json27-Mar-2024 21:39 14K 
[   ]mmlu_machine_learning_mmlu_machine_learning_subject:machine_learning.json27-Mar-2024 21:39 14K 
[   ]mmlu_logical_fallacies_mmlu_logical_fallacies_subject:logical_fallacies.json27-Mar-2024 21:39 15K 
[   ]mmlu_international_law_mmlu_international_law_subject:international_law.json27-Mar-2024 21:39 15K 
[   ]mmlu_human_sexuality_mmlu_human_sexuality_subject:human_sexuality.json27-Mar-2024 21:39 14K 
[   ]mmlu_human_aging_mmlu_human_aging_subject:human_aging.json27-Mar-2024 21:39 14K 
[   ]mmlu_high_school_world_history_mmlu_high_school_world_history_subject:high_school_world_history.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_us_history_mmlu_high_school_us_history_subject:high_school_us_history.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_statistics_mmlu_high_school_statistics_subject:high_school_statistics.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_psychology_mmlu_high_school_psychology_subject:high_school_psychology.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_physics_mmlu_high_school_physics_subject:high_school_physics.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_microeconomics_mmlu_high_school_microeconomics_subject:high_school_microeconomics.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_mathematics_mmlu_high_school_mathematics_subject:high_school_mathematics.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_macroeconomics_mmlu_high_school_macroeconomics_subject:high_school_macroeconomics.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_government_and_politics_mmlu_high_school_government_and_politics_subject:high_school_government_and_politics.json27-Mar-2024 21:39 16K 
[   ]mmlu_high_school_geography_mmlu_high_school_geography_subject:high_school_geography.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_european_history_mmlu_high_school_european_history_subject:high_school_european_history.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_computer_science_mmlu_high_school_computer_science_subject:high_school_computer_science.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_chemistry_mmlu_high_school_chemistry_subject:high_school_chemistry.json27-Mar-2024 21:39 15K 
[   ]mmlu_high_school_biology_mmlu_high_school_biology_subject:high_school_biology.json27-Mar-2024 21:39 15K 
[   ]mmlu_formal_logic_mmlu_formal_logic_subject:formal_logic.json27-Mar-2024 21:39 14K 
[   ]mmlu_elementary_mathematics_mmlu_elementary_mathematics_subject:elementary_mathematics.json27-Mar-2024 21:39 15K 
[   ]mmlu_electrical_engineering_mmlu_electrical_engineering_subject:electrical_engineering.json27-Mar-2024 21:39 15K 
[   ]mmlu_conceptual_physics_mmlu_conceptual_physics_subject:conceptual_physics.json27-Mar-2024 21:39 15K 
[   ]mmlu_college_physics_mmlu_college_physics_subject:college_physics.json27-Mar-2024 21:39 14K 
[   ]mmlu_college_medicine_mmlu_college_medicine_subject:college_medicine.json27-Mar-2024 21:39 14K 
[   ]mmlu_college_mathematics_mmlu_college_mathematics_subject:college_mathematics.json27-Mar-2024 21:39 15K 
[   ]mmlu_college_computer_science_mmlu_college_computer_science_subject:college_computer_science.json27-Mar-2024 21:39 15K 
[   ]mmlu_college_biology_mmlu_college_biology_subject:college_biology.json27-Mar-2024 21:39 14K 
[   ]mmlu_clinical_knowledge_mmlu_clinical_knowledge_subject:clinical_knowledge.json27-Mar-2024 21:39 15K 
[   ]mmlu_business_ethics_mmlu_business_ethics_subject:business_ethics.json27-Mar-2024 21:39 14K 
[   ]mmlu_astronomy_mmlu_astronomy_subject:astronomy.json27-Mar-2024 21:39 14K 
[   ]mmlu_us_foreign_policy_mmlu_us_foreign_policy_subject:us_foreign_policy.json27-Mar-2024 21:39 36K 
[   ]mmlu_professional_medicine_mmlu_professional_medicine_subject:professional_medicine.json27-Mar-2024 21:39 15K 
[   ]mmlu_philosophy_mmlu_philosophy_subject:philosophy.json27-Mar-2024 21:39 14K 
[   ]mmlu_jurisprudence_mmlu_jurisprudence_subject:jurisprudence.json27-Mar-2024 21:39 14K 
[   ]mmlu_global_facts_mmlu_global_facts_subject:global_facts.json27-Mar-2024 21:39 14K 
[   ]mmlu_econometrics_mmlu_econometrics_subject:econometrics.json27-Mar-2024 21:39 35K 
[   ]mmlu_computer_security_mmlu_computer_security_subject:computer_security.json27-Mar-2024 21:39 36K 
[   ]mmlu_college_chemistry_mmlu_college_chemistry_subject:college_chemistry.json27-Mar-2024 21:39 36K 
[   ]mmlu_anatomy_mmlu_anatomy_subject:anatomy.json27-Mar-2024 21:39 14K 
[   ]mmlu_abstract_algebra_mmlu_abstract_algebra_subject:abstract_algebra.json27-Mar-2024 21:39 36K 
[   ]mmlu_mmlu_subject:world_religions.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:virology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:us_foreign_policy.json27-Mar-2024 21:39 37K 
[   ]mmlu_mmlu_subject:sociology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:security_studies.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:public_relations.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:professional_psychology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:professional_medicine.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:professional_law.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:professional_accounting.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:prehistory.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:philosophy.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:nutrition.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:moral_scenarios.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:moral_disputes.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:miscellaneous.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:medical_genetics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:marketing.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:management.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:machine_learning.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:logical_fallacies.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:jurisprudence.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:international_law.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:human_sexuality.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:human_aging.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_world_history.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_us_history.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_statistics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_psychology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_physics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_microeconomics.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_mathematics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_macroeconomics.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_government_and_politics.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_geography.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_european_history.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_computer_science.json27-Mar-2024 21:39 18K 
[   ]mmlu_mmlu_subject:high_school_chemistry.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:high_school_biology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:global_facts.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:formal_logic.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:elementary_mathematics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:electrical_engineering.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:econometrics.json27-Mar-2024 21:39 37K 
[   ]mmlu_mmlu_subject:conceptual_physics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:computer_security.json27-Mar-2024 21:39 37K 
[   ]mmlu_mmlu_subject:college_physics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:college_medicine.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:college_mathematics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:college_computer_science.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:college_chemistry.json27-Mar-2024 21:39 37K 
[   ]mmlu_mmlu_subject:college_biology.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:clinical_knowledge.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:business_ethics.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:astronomy.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:anatomy.json27-Mar-2024 21:39 17K 
[   ]mmlu_mmlu_subject:abstract_algebra.json27-Mar-2024 21:39 37K 
[   ]mmlu_mmlu.json27-Mar-2024 21:39 625K 
[   ]mmlu_subjects_general_information.json27-Mar-2024 21:39 1.1M 
[   ]mmlu_subjects_efficiency.json27-Mar-2024 21:39 248K 
[   ]mmlu_subjects_accuracy.json27-Mar-2024 21:39 241K 
[   ]calibration_accuracy.json11-Mar-2024 11:47 57K 
[   ]calibration_calibration_detailed.json11-Mar-2024 11:47 95K 
[   ]knowledge_general_information.json11-Mar-2024 11:47 342K 
[   ]knowledge_efficiency.json11-Mar-2024 11:47 9.1K 
[   ]knowledge_toxicity.json11-Mar-2024 11:47 2.9K 
[   ]knowledge_bias.json11-Mar-2024 11:47 7.8K 
[   ]knowledge_fairness.json11-Mar-2024 11:47 59K 
[   ]knowledge_robustness.json11-Mar-2024 11:47 59K 
[   ]knowledge_calibration.json11-Mar-2024 11:47 8.5K 
[   ]knowledge_accuracy.json11-Mar-2024 11:47 59K 
[   ]question_answering_toxicity.json11-Mar-2024 11:47 7.3K 
[   ]question_answering_bias.json11-Mar-2024 11:47 30K 
[   ]question_answering_general_information.json11-Mar-2024 11:47 360K 
[   ]question_answering_efficiency.json11-Mar-2024 11:47 13K 
[   ]question_answering_fairness.json11-Mar-2024 11:47 64K 
[   ]question_answering_robustness.json11-Mar-2024 11:47 64K 
[   ]question_answering_calibration.json11-Mar-2024 11:47 14K 
[   ]question_answering_accuracy.json11-Mar-2024 11:47 62K 
[   ]targeted_evaluations_efficiency_detailed.json11-Mar-2024 11:47 326K 
[   ]targeted_evaluations_bbq_metrics.json11-Mar-2024 11:47 4.0K 
[   ]targeted_evaluations_disinformation_metrics.json11-Mar-2024 11:47 6.2K 
[   ]targeted_evaluations_copyright_metrics.json11-Mar-2024 11:47 8.4K 
[   ]targeted_evaluations_apps_metrics.json11-Mar-2024 11:47 4.0K 
[   ]targeted_evaluations_toxicity.json11-Mar-2024 11:47 9.6K 
[   ]targeted_evaluations_bias.json11-Mar-2024 11:47 42K 
[   ]targeted_evaluations_fairness.json11-Mar-2024 11:47 59K 
[   ]targeted_evaluations_robustness.json11-Mar-2024 11:47 59K 
[   ]targeted_evaluations_calibration.json11-Mar-2024 11:47 8.5K 
[   ]targeted_evaluations_general_information.json11-Mar-2024 11:47 497K 
[   ]targeted_evaluations_accuracy.json11-Mar-2024 11:47 78K 
[   ]core_scenarios_summarization_metrics.json11-Mar-2024 11:47 22K 
[   ]core_scenarios_toxicity.json11-Mar-2024 11:47 15K 
[   ]core_scenarios_bias.json11-Mar-2024 11:47 70K 
[   ]core_scenarios_general_information.json11-Mar-2024 11:47 403K 
[   ]core_scenarios_efficiency.json11-Mar-2024 11:47 21K 
[   ]core_scenarios_fairness.json11-Mar-2024 11:47 70K 
[   ]core_scenarios_robustness.json11-Mar-2024 11:47 70K 
[   ]core_scenarios_calibration.json11-Mar-2024 11:47 18K 
[   ]core_scenarios_accuracy.json11-Mar-2024 11:47 70K 

Apache/2.2.15 (CentOS) Server at nlp.stanford.edu Port 443