Directory listing for /.local/lib/python3.10/site-packages/lm_eval/tasks/openai-mmmlu/default/
__pycache__/
_default_template_yaml
_mmmlu.yaml
_mmmlu_ar_xy.yaml
_mmmlu_ar_xy_humanities.yaml
_mmmlu_ar_xy_other.yaml
_mmmlu_ar_xy_social_sciences.yaml
_mmmlu_ar_xy_stem.yaml
_mmmlu_bn_bd.yaml
_mmmlu_bn_bd_humanities.yaml
_mmmlu_bn_bd_other.yaml
_mmmlu_bn_bd_social_sciences.yaml
_mmmlu_bn_bd_stem.yaml
_mmmlu_de_de.yaml
_mmmlu_de_de_humanities.yaml
_mmmlu_de_de_other.yaml
_mmmlu_de_de_social_sciences.yaml
_mmmlu_de_de_stem.yaml
_mmmlu_es_la.yaml
_mmmlu_es_la_humanities.yaml
_mmmlu_es_la_other.yaml
_mmmlu_es_la_social_sciences.yaml
_mmmlu_es_la_stem.yaml
_mmmlu_fr_fr.yaml
_mmmlu_fr_fr_humanities.yaml
_mmmlu_fr_fr_other.yaml
_mmmlu_fr_fr_social_sciences.yaml
_mmmlu_fr_fr_stem.yaml
_mmmlu_hi_in.yaml
_mmmlu_hi_in_humanities.yaml
_mmmlu_hi_in_other.yaml
_mmmlu_hi_in_social_sciences.yaml
_mmmlu_hi_in_stem.yaml
_mmmlu_id_id.yaml
_mmmlu_id_id_humanities.yaml
_mmmlu_id_id_other.yaml
_mmmlu_id_id_social_sciences.yaml
_mmmlu_id_id_stem.yaml
_mmmlu_it_it.yaml
_mmmlu_it_it_humanities.yaml
_mmmlu_it_it_other.yaml
_mmmlu_it_it_social_sciences.yaml
_mmmlu_it_it_stem.yaml
_mmmlu_ja_jp.yaml
_mmmlu_ja_jp_humanities.yaml
_mmmlu_ja_jp_other.yaml
_mmmlu_ja_jp_social_sciences.yaml
_mmmlu_ja_jp_stem.yaml
_mmmlu_ko_kr.yaml
_mmmlu_ko_kr_humanities.yaml
_mmmlu_ko_kr_other.yaml
_mmmlu_ko_kr_social_sciences.yaml
_mmmlu_ko_kr_stem.yaml
_mmmlu_pt_br.yaml
_mmmlu_pt_br_humanities.yaml
_mmmlu_pt_br_other.yaml
_mmmlu_pt_br_social_sciences.yaml
_mmmlu_pt_br_stem.yaml
_mmmlu_sw_ke.yaml
_mmmlu_sw_ke_humanities.yaml
_mmmlu_sw_ke_other.yaml
_mmmlu_sw_ke_social_sciences.yaml
_mmmlu_sw_ke_stem.yaml
_mmmlu_yo_ng.yaml
_mmmlu_yo_ng_humanities.yaml
_mmmlu_yo_ng_other.yaml
_mmmlu_yo_ng_social_sciences.yaml
_mmmlu_yo_ng_stem.yaml
_mmmlu_zh_cn.yaml
_mmmlu_zh_cn_humanities.yaml
_mmmlu_zh_cn_other.yaml
_mmmlu_zh_cn_social_sciences.yaml
_mmmlu_zh_cn_stem.yaml
mmmlu_ar_xy_abstract_algebra.yaml
mmmlu_ar_xy_anatomy.yaml
mmmlu_ar_xy_astronomy.yaml
mmmlu_ar_xy_business_ethics.yaml
mmmlu_ar_xy_clinical_knowledge.yaml
mmmlu_ar_xy_college_biology.yaml
mmmlu_ar_xy_college_chemistry.yaml
mmmlu_ar_xy_college_computer_science.yaml
mmmlu_ar_xy_college_mathematics.yaml
mmmlu_ar_xy_college_medicine.yaml
mmmlu_ar_xy_college_physics.yaml
mmmlu_ar_xy_computer_security.yaml
mmmlu_ar_xy_conceptual_physics.yaml
mmmlu_ar_xy_econometrics.yaml
mmmlu_ar_xy_electrical_engineering.yaml
mmmlu_ar_xy_elementary_mathematics.yaml
mmmlu_ar_xy_formal_logic.yaml
mmmlu_ar_xy_global_facts.yaml
mmmlu_ar_xy_high_school_biology.yaml
mmmlu_ar_xy_high_school_chemistry.yaml
mmmlu_ar_xy_high_school_computer_science.yaml
mmmlu_ar_xy_high_school_european_history.yaml
mmmlu_ar_xy_high_school_geography.yaml
mmmlu_ar_xy_high_school_government_and_politics.yaml
mmmlu_ar_xy_high_school_macroeconomics.yaml
mmmlu_ar_xy_high_school_mathematics.yaml
mmmlu_ar_xy_high_school_microeconomics.yaml
mmmlu_ar_xy_high_school_physics.yaml
mmmlu_ar_xy_high_school_psychology.yaml
mmmlu_ar_xy_high_school_statistics.yaml
mmmlu_ar_xy_high_school_us_history.yaml
mmmlu_ar_xy_high_school_world_history.yaml
mmmlu_ar_xy_human_aging.yaml
mmmlu_ar_xy_human_sexuality.yaml
mmmlu_ar_xy_international_law.yaml
mmmlu_ar_xy_jurisprudence.yaml
mmmlu_ar_xy_logical_fallacies.yaml
mmmlu_ar_xy_machine_learning.yaml
mmmlu_ar_xy_management.yaml
mmmlu_ar_xy_marketing.yaml
mmmlu_ar_xy_medical_genetics.yaml
mmmlu_ar_xy_miscellaneous.yaml
mmmlu_ar_xy_moral_disputes.yaml
mmmlu_ar_xy_moral_scenarios.yaml
mmmlu_ar_xy_nutrition.yaml
mmmlu_ar_xy_philosophy.yaml
mmmlu_ar_xy_prehistory.yaml
mmmlu_ar_xy_professional_accounting.yaml
mmmlu_ar_xy_professional_law.yaml
mmmlu_ar_xy_professional_medicine.yaml
mmmlu_ar_xy_professional_psychology.yaml
mmmlu_ar_xy_public_relations.yaml
mmmlu_ar_xy_security_studies.yaml
mmmlu_ar_xy_sociology.yaml
mmmlu_ar_xy_us_foreign_policy.yaml
mmmlu_ar_xy_virology.yaml
mmmlu_ar_xy_world_religions.yaml
mmmlu_bn_bd_abstract_algebra.yaml
mmmlu_bn_bd_anatomy.yaml
mmmlu_bn_bd_astronomy.yaml
mmmlu_bn_bd_business_ethics.yaml
mmmlu_bn_bd_clinical_knowledge.yaml
mmmlu_bn_bd_college_biology.yaml
mmmlu_bn_bd_college_chemistry.yaml
mmmlu_bn_bd_college_computer_science.yaml
mmmlu_bn_bd_college_mathematics.yaml
mmmlu_bn_bd_college_medicine.yaml
mmmlu_bn_bd_college_physics.yaml
mmmlu_bn_bd_computer_security.yaml
mmmlu_bn_bd_conceptual_physics.yaml
mmmlu_bn_bd_econometrics.yaml
mmmlu_bn_bd_electrical_engineering.yaml
mmmlu_bn_bd_elementary_mathematics.yaml
mmmlu_bn_bd_formal_logic.yaml
mmmlu_bn_bd_global_facts.yaml
mmmlu_bn_bd_high_school_biology.yaml
mmmlu_bn_bd_high_school_chemistry.yaml
mmmlu_bn_bd_high_school_computer_science.yaml
mmmlu_bn_bd_high_school_european_history.yaml
mmmlu_bn_bd_high_school_geography.yaml
mmmlu_bn_bd_high_school_government_and_politics.yaml
mmmlu_bn_bd_high_school_macroeconomics.yaml
mmmlu_bn_bd_high_school_mathematics.yaml
mmmlu_bn_bd_high_school_microeconomics.yaml
mmmlu_bn_bd_high_school_physics.yaml
mmmlu_bn_bd_high_school_psychology.yaml
mmmlu_bn_bd_high_school_statistics.yaml
mmmlu_bn_bd_high_school_us_history.yaml
mmmlu_bn_bd_high_school_world_history.yaml
mmmlu_bn_bd_human_aging.yaml
mmmlu_bn_bd_human_sexuality.yaml
mmmlu_bn_bd_international_law.yaml
mmmlu_bn_bd_jurisprudence.yaml
mmmlu_bn_bd_logical_fallacies.yaml
mmmlu_bn_bd_machine_learning.yaml
mmmlu_bn_bd_management.yaml
mmmlu_bn_bd_marketing.yaml
mmmlu_bn_bd_medical_genetics.yaml
mmmlu_bn_bd_miscellaneous.yaml
mmmlu_bn_bd_moral_disputes.yaml
mmmlu_bn_bd_moral_scenarios.yaml
mmmlu_bn_bd_nutrition.yaml
mmmlu_bn_bd_philosophy.yaml
mmmlu_bn_bd_prehistory.yaml
mmmlu_bn_bd_professional_accounting.yaml
mmmlu_bn_bd_professional_law.yaml
mmmlu_bn_bd_professional_medicine.yaml
mmmlu_bn_bd_professional_psychology.yaml
mmmlu_bn_bd_public_relations.yaml
mmmlu_bn_bd_security_studies.yaml
mmmlu_bn_bd_sociology.yaml
mmmlu_bn_bd_us_foreign_policy.yaml
mmmlu_bn_bd_virology.yaml
mmmlu_bn_bd_world_religions.yaml
mmmlu_de_de_abstract_algebra.yaml
mmmlu_de_de_anatomy.yaml
mmmlu_de_de_astronomy.yaml
mmmlu_de_de_business_ethics.yaml
mmmlu_de_de_clinical_knowledge.yaml
mmmlu_de_de_college_biology.yaml
mmmlu_de_de_college_chemistry.yaml
mmmlu_de_de_college_computer_science.yaml
mmmlu_de_de_college_mathematics.yaml
mmmlu_de_de_college_medicine.yaml
mmmlu_de_de_college_physics.yaml
mmmlu_de_de_computer_security.yaml
mmmlu_de_de_conceptual_physics.yaml
mmmlu_de_de_econometrics.yaml
mmmlu_de_de_electrical_engineering.yaml
mmmlu_de_de_elementary_mathematics.yaml
mmmlu_de_de_formal_logic.yaml
mmmlu_de_de_global_facts.yaml
mmmlu_de_de_high_school_biology.yaml
mmmlu_de_de_high_school_chemistry.yaml
mmmlu_de_de_high_school_computer_science.yaml
mmmlu_de_de_high_school_european_history.yaml
mmmlu_de_de_high_school_geography.yaml
mmmlu_de_de_high_school_government_and_politics.yaml
mmmlu_de_de_high_school_macroeconomics.yaml
mmmlu_de_de_high_school_mathematics.yaml
mmmlu_de_de_high_school_microeconomics.yaml
mmmlu_de_de_high_school_physics.yaml
mmmlu_de_de_high_school_psychology.yaml
mmmlu_de_de_high_school_statistics.yaml
mmmlu_de_de_high_school_us_history.yaml
mmmlu_de_de_high_school_world_history.yaml
mmmlu_de_de_human_aging.yaml
mmmlu_de_de_human_sexuality.yaml
mmmlu_de_de_international_law.yaml
mmmlu_de_de_jurisprudence.yaml
mmmlu_de_de_logical_fallacies.yaml
mmmlu_de_de_machine_learning.yaml
mmmlu_de_de_management.yaml
mmmlu_de_de_marketing.yaml
mmmlu_de_de_medical_genetics.yaml
mmmlu_de_de_miscellaneous.yaml
mmmlu_de_de_moral_disputes.yaml
mmmlu_de_de_moral_scenarios.yaml
mmmlu_de_de_nutrition.yaml
mmmlu_de_de_philosophy.yaml
mmmlu_de_de_prehistory.yaml
mmmlu_de_de_professional_accounting.yaml
mmmlu_de_de_professional_law.yaml
mmmlu_de_de_professional_medicine.yaml
mmmlu_de_de_professional_psychology.yaml
mmmlu_de_de_public_relations.yaml
mmmlu_de_de_security_studies.yaml
mmmlu_de_de_sociology.yaml
mmmlu_de_de_us_foreign_policy.yaml
mmmlu_de_de_virology.yaml
mmmlu_de_de_world_religions.yaml
mmmlu_es_la_abstract_algebra.yaml
mmmlu_es_la_anatomy.yaml
mmmlu_es_la_astronomy.yaml
mmmlu_es_la_business_ethics.yaml
mmmlu_es_la_clinical_knowledge.yaml
mmmlu_es_la_college_biology.yaml
mmmlu_es_la_college_chemistry.yaml
mmmlu_es_la_college_computer_science.yaml
mmmlu_es_la_college_mathematics.yaml
mmmlu_es_la_college_medicine.yaml
mmmlu_es_la_college_physics.yaml
mmmlu_es_la_computer_security.yaml
mmmlu_es_la_conceptual_physics.yaml
mmmlu_es_la_econometrics.yaml
mmmlu_es_la_electrical_engineering.yaml
mmmlu_es_la_elementary_mathematics.yaml
mmmlu_es_la_formal_logic.yaml
mmmlu_es_la_global_facts.yaml
mmmlu_es_la_high_school_biology.yaml
mmmlu_es_la_high_school_chemistry.yaml
mmmlu_es_la_high_school_computer_science.yaml
mmmlu_es_la_high_school_european_history.yaml
mmmlu_es_la_high_school_geography.yaml
mmmlu_es_la_high_school_government_and_politics.yaml
mmmlu_es_la_high_school_macroeconomics.yaml
mmmlu_es_la_high_school_mathematics.yaml
mmmlu_es_la_high_school_microeconomics.yaml
mmmlu_es_la_high_school_physics.yaml
mmmlu_es_la_high_school_psychology.yaml
mmmlu_es_la_high_school_statistics.yaml
mmmlu_es_la_high_school_us_history.yaml
mmmlu_es_la_high_school_world_history.yaml
mmmlu_es_la_human_aging.yaml
mmmlu_es_la_human_sexuality.yaml
mmmlu_es_la_international_law.yaml
mmmlu_es_la_jurisprudence.yaml
mmmlu_es_la_logical_fallacies.yaml
mmmlu_es_la_machine_learning.yaml
mmmlu_es_la_management.yaml
mmmlu_es_la_marketing.yaml
mmmlu_es_la_medical_genetics.yaml
mmmlu_es_la_miscellaneous.yaml
mmmlu_es_la_moral_disputes.yaml
mmmlu_es_la_moral_scenarios.yaml
mmmlu_es_la_nutrition.yaml
mmmlu_es_la_philosophy.yaml
mmmlu_es_la_prehistory.yaml
mmmlu_es_la_professional_accounting.yaml
mmmlu_es_la_professional_law.yaml
mmmlu_es_la_professional_medicine.yaml
mmmlu_es_la_professional_psychology.yaml
mmmlu_es_la_public_relations.yaml
mmmlu_es_la_security_studies.yaml
mmmlu_es_la_sociology.yaml
mmmlu_es_la_us_foreign_policy.yaml
mmmlu_es_la_virology.yaml
mmmlu_es_la_world_religions.yaml
mmmlu_fr_fr_abstract_algebra.yaml
mmmlu_fr_fr_anatomy.yaml
mmmlu_fr_fr_astronomy.yaml
mmmlu_fr_fr_business_ethics.yaml
mmmlu_fr_fr_clinical_knowledge.yaml
mmmlu_fr_fr_college_biology.yaml
mmmlu_fr_fr_college_chemistry.yaml
mmmlu_fr_fr_college_computer_science.yaml
mmmlu_fr_fr_college_mathematics.yaml
mmmlu_fr_fr_college_medicine.yaml
mmmlu_fr_fr_college_physics.yaml
mmmlu_fr_fr_computer_security.yaml
mmmlu_fr_fr_conceptual_physics.yaml
mmmlu_fr_fr_econometrics.yaml
mmmlu_fr_fr_electrical_engineering.yaml
mmmlu_fr_fr_elementary_mathematics.yaml
mmmlu_fr_fr_formal_logic.yaml
mmmlu_fr_fr_global_facts.yaml
mmmlu_fr_fr_high_school_biology.yaml
mmmlu_fr_fr_high_school_chemistry.yaml
mmmlu_fr_fr_high_school_computer_science.yaml
mmmlu_fr_fr_high_school_european_history.yaml
mmmlu_fr_fr_high_school_geography.yaml
mmmlu_fr_fr_high_school_government_and_politics.yaml
mmmlu_fr_fr_high_school_macroeconomics.yaml
mmmlu_fr_fr_high_school_mathematics.yaml
mmmlu_fr_fr_high_school_microeconomics.yaml
mmmlu_fr_fr_high_school_physics.yaml
mmmlu_fr_fr_high_school_psychology.yaml
mmmlu_fr_fr_high_school_statistics.yaml
mmmlu_fr_fr_high_school_us_history.yaml
mmmlu_fr_fr_high_school_world_history.yaml
mmmlu_fr_fr_human_aging.yaml
mmmlu_fr_fr_human_sexuality.yaml
mmmlu_fr_fr_international_law.yaml
mmmlu_fr_fr_jurisprudence.yaml
mmmlu_fr_fr_logical_fallacies.yaml
mmmlu_fr_fr_machine_learning.yaml
mmmlu_fr_fr_management.yaml
mmmlu_fr_fr_marketing.yaml
mmmlu_fr_fr_medical_genetics.yaml
mmmlu_fr_fr_miscellaneous.yaml
mmmlu_fr_fr_moral_disputes.yaml
mmmlu_fr_fr_moral_scenarios.yaml
mmmlu_fr_fr_nutrition.yaml
mmmlu_fr_fr_philosophy.yaml
mmmlu_fr_fr_prehistory.yaml
mmmlu_fr_fr_professional_accounting.yaml
mmmlu_fr_fr_professional_law.yaml
mmmlu_fr_fr_professional_medicine.yaml
mmmlu_fr_fr_professional_psychology.yaml
mmmlu_fr_fr_public_relations.yaml
mmmlu_fr_fr_security_studies.yaml
mmmlu_fr_fr_sociology.yaml
mmmlu_fr_fr_us_foreign_policy.yaml
mmmlu_fr_fr_virology.yaml
mmmlu_fr_fr_world_religions.yaml
mmmlu_hi_in_abstract_algebra.yaml
mmmlu_hi_in_anatomy.yaml
mmmlu_hi_in_astronomy.yaml
mmmlu_hi_in_business_ethics.yaml
mmmlu_hi_in_clinical_knowledge.yaml
mmmlu_hi_in_college_biology.yaml
mmmlu_hi_in_college_chemistry.yaml
mmmlu_hi_in_college_computer_science.yaml
mmmlu_hi_in_college_mathematics.yaml
mmmlu_hi_in_college_medicine.yaml
mmmlu_hi_in_college_physics.yaml
mmmlu_hi_in_computer_security.yaml
mmmlu_hi_in_conceptual_physics.yaml
mmmlu_hi_in_econometrics.yaml
mmmlu_hi_in_electrical_engineering.yaml
mmmlu_hi_in_elementary_mathematics.yaml
mmmlu_hi_in_formal_logic.yaml
mmmlu_hi_in_global_facts.yaml
mmmlu_hi_in_high_school_biology.yaml
mmmlu_hi_in_high_school_chemistry.yaml
mmmlu_hi_in_high_school_computer_science.yaml
mmmlu_hi_in_high_school_european_history.yaml
mmmlu_hi_in_high_school_geography.yaml
mmmlu_hi_in_high_school_government_and_politics.yaml
mmmlu_hi_in_high_school_macroeconomics.yaml
mmmlu_hi_in_high_school_mathematics.yaml
mmmlu_hi_in_high_school_microeconomics.yaml
mmmlu_hi_in_high_school_physics.yaml
mmmlu_hi_in_high_school_psychology.yaml
mmmlu_hi_in_high_school_statistics.yaml
mmmlu_hi_in_high_school_us_history.yaml
mmmlu_hi_in_high_school_world_history.yaml
mmmlu_hi_in_human_aging.yaml
mmmlu_hi_in_human_sexuality.yaml
mmmlu_hi_in_international_law.yaml
mmmlu_hi_in_jurisprudence.yaml
mmmlu_hi_in_logical_fallacies.yaml
mmmlu_hi_in_machine_learning.yaml
mmmlu_hi_in_management.yaml
mmmlu_hi_in_marketing.yaml
mmmlu_hi_in_medical_genetics.yaml
mmmlu_hi_in_miscellaneous.yaml
mmmlu_hi_in_moral_disputes.yaml
mmmlu_hi_in_moral_scenarios.yaml
mmmlu_hi_in_nutrition.yaml
mmmlu_hi_in_philosophy.yaml
mmmlu_hi_in_prehistory.yaml
mmmlu_hi_in_professional_accounting.yaml
mmmlu_hi_in_professional_law.yaml
mmmlu_hi_in_professional_medicine.yaml
mmmlu_hi_in_professional_psychology.yaml
mmmlu_hi_in_public_relations.yaml
mmmlu_hi_in_security_studies.yaml
mmmlu_hi_in_sociology.yaml
mmmlu_hi_in_us_foreign_policy.yaml
mmmlu_hi_in_virology.yaml
mmmlu_hi_in_world_religions.yaml
mmmlu_id_id_abstract_algebra.yaml
mmmlu_id_id_anatomy.yaml
mmmlu_id_id_astronomy.yaml
mmmlu_id_id_business_ethics.yaml
mmmlu_id_id_clinical_knowledge.yaml
mmmlu_id_id_college_biology.yaml
mmmlu_id_id_college_chemistry.yaml
mmmlu_id_id_college_computer_science.yaml
mmmlu_id_id_college_mathematics.yaml
mmmlu_id_id_college_medicine.yaml
mmmlu_id_id_college_physics.yaml
mmmlu_id_id_computer_security.yaml
mmmlu_id_id_conceptual_physics.yaml
mmmlu_id_id_econometrics.yaml
mmmlu_id_id_electrical_engineering.yaml
mmmlu_id_id_elementary_mathematics.yaml
mmmlu_id_id_formal_logic.yaml
mmmlu_id_id_global_facts.yaml
mmmlu_id_id_high_school_biology.yaml
mmmlu_id_id_high_school_chemistry.yaml
mmmlu_id_id_high_school_computer_science.yaml
mmmlu_id_id_high_school_european_history.yaml
mmmlu_id_id_high_school_geography.yaml
mmmlu_id_id_high_school_government_and_politics.yaml
mmmlu_id_id_high_school_macroeconomics.yaml
mmmlu_id_id_high_school_mathematics.yaml
mmmlu_id_id_high_school_microeconomics.yaml
mmmlu_id_id_high_school_physics.yaml
mmmlu_id_id_high_school_psychology.yaml
mmmlu_id_id_high_school_statistics.yaml
mmmlu_id_id_high_school_us_history.yaml
mmmlu_id_id_high_school_world_history.yaml
mmmlu_id_id_human_aging.yaml
mmmlu_id_id_human_sexuality.yaml
mmmlu_id_id_international_law.yaml
mmmlu_id_id_jurisprudence.yaml
mmmlu_id_id_logical_fallacies.yaml
mmmlu_id_id_machine_learning.yaml
mmmlu_id_id_management.yaml
mmmlu_id_id_marketing.yaml
mmmlu_id_id_medical_genetics.yaml
mmmlu_id_id_miscellaneous.yaml
mmmlu_id_id_moral_disputes.yaml
mmmlu_id_id_moral_scenarios.yaml
mmmlu_id_id_nutrition.yaml
mmmlu_id_id_philosophy.yaml
mmmlu_id_id_prehistory.yaml
mmmlu_id_id_professional_accounting.yaml
mmmlu_id_id_professional_law.yaml
mmmlu_id_id_professional_medicine.yaml
mmmlu_id_id_professional_psychology.yaml
mmmlu_id_id_public_relations.yaml
mmmlu_id_id_security_studies.yaml
mmmlu_id_id_sociology.yaml
mmmlu_id_id_us_foreign_policy.yaml
mmmlu_id_id_virology.yaml
mmmlu_id_id_world_religions.yaml
mmmlu_it_it_abstract_algebra.yaml
mmmlu_it_it_anatomy.yaml
mmmlu_it_it_astronomy.yaml
mmmlu_it_it_business_ethics.yaml
mmmlu_it_it_clinical_knowledge.yaml
mmmlu_it_it_college_biology.yaml
mmmlu_it_it_college_chemistry.yaml
mmmlu_it_it_college_computer_science.yaml
mmmlu_it_it_college_mathematics.yaml
mmmlu_it_it_college_medicine.yaml
mmmlu_it_it_college_physics.yaml
mmmlu_it_it_computer_security.yaml
mmmlu_it_it_conceptual_physics.yaml
mmmlu_it_it_econometrics.yaml
mmmlu_it_it_electrical_engineering.yaml
mmmlu_it_it_elementary_mathematics.yaml
mmmlu_it_it_formal_logic.yaml
mmmlu_it_it_global_facts.yaml
mmmlu_it_it_high_school_biology.yaml
mmmlu_it_it_high_school_chemistry.yaml
mmmlu_it_it_high_school_computer_science.yaml
mmmlu_it_it_high_school_european_history.yaml
mmmlu_it_it_high_school_geography.yaml
mmmlu_it_it_high_school_government_and_politics.yaml
mmmlu_it_it_high_school_macroeconomics.yaml
mmmlu_it_it_high_school_mathematics.yaml
mmmlu_it_it_high_school_microeconomics.yaml
mmmlu_it_it_high_school_physics.yaml
mmmlu_it_it_high_school_psychology.yaml
mmmlu_it_it_high_school_statistics.yaml
mmmlu_it_it_high_school_us_history.yaml
mmmlu_it_it_high_school_world_history.yaml
mmmlu_it_it_human_aging.yaml
mmmlu_it_it_human_sexuality.yaml
mmmlu_it_it_international_law.yaml
mmmlu_it_it_jurisprudence.yaml
mmmlu_it_it_logical_fallacies.yaml
mmmlu_it_it_machine_learning.yaml
mmmlu_it_it_management.yaml
mmmlu_it_it_marketing.yaml
mmmlu_it_it_medical_genetics.yaml
mmmlu_it_it_miscellaneous.yaml
mmmlu_it_it_moral_disputes.yaml
mmmlu_it_it_moral_scenarios.yaml
mmmlu_it_it_nutrition.yaml
mmmlu_it_it_philosophy.yaml
mmmlu_it_it_prehistory.yaml
mmmlu_it_it_professional_accounting.yaml
mmmlu_it_it_professional_law.yaml
mmmlu_it_it_professional_medicine.yaml
mmmlu_it_it_professional_psychology.yaml
mmmlu_it_it_public_relations.yaml
mmmlu_it_it_security_studies.yaml
mmmlu_it_it_sociology.yaml
mmmlu_it_it_us_foreign_policy.yaml
mmmlu_it_it_virology.yaml
mmmlu_it_it_world_religions.yaml
mmmlu_ja_jp_abstract_algebra.yaml
mmmlu_ja_jp_anatomy.yaml
mmmlu_ja_jp_astronomy.yaml
mmmlu_ja_jp_business_ethics.yaml
mmmlu_ja_jp_clinical_knowledge.yaml
mmmlu_ja_jp_college_biology.yaml
mmmlu_ja_jp_college_chemistry.yaml
mmmlu_ja_jp_college_computer_science.yaml
mmmlu_ja_jp_college_mathematics.yaml
mmmlu_ja_jp_college_medicine.yaml
mmmlu_ja_jp_college_physics.yaml
mmmlu_ja_jp_computer_security.yaml
mmmlu_ja_jp_conceptual_physics.yaml
mmmlu_ja_jp_econometrics.yaml
mmmlu_ja_jp_electrical_engineering.yaml
mmmlu_ja_jp_elementary_mathematics.yaml
mmmlu_ja_jp_formal_logic.yaml
mmmlu_ja_jp_global_facts.yaml
mmmlu_ja_jp_high_school_biology.yaml
mmmlu_ja_jp_high_school_chemistry.yaml
mmmlu_ja_jp_high_school_computer_science.yaml
mmmlu_ja_jp_high_school_european_history.yaml
mmmlu_ja_jp_high_school_geography.yaml
mmmlu_ja_jp_high_school_government_and_politics.yaml
mmmlu_ja_jp_high_school_macroeconomics.yaml
mmmlu_ja_jp_high_school_mathematics.yaml
mmmlu_ja_jp_high_school_microeconomics.yaml
mmmlu_ja_jp_high_school_physics.yaml
mmmlu_ja_jp_high_school_psychology.yaml
mmmlu_ja_jp_high_school_statistics.yaml
mmmlu_ja_jp_high_school_us_history.yaml
mmmlu_ja_jp_high_school_world_history.yaml
mmmlu_ja_jp_human_aging.yaml
mmmlu_ja_jp_human_sexuality.yaml
mmmlu_ja_jp_international_law.yaml
mmmlu_ja_jp_jurisprudence.yaml
mmmlu_ja_jp_logical_fallacies.yaml
mmmlu_ja_jp_machine_learning.yaml
mmmlu_ja_jp_management.yaml
mmmlu_ja_jp_marketing.yaml
mmmlu_ja_jp_medical_genetics.yaml
mmmlu_ja_jp_miscellaneous.yaml
mmmlu_ja_jp_moral_disputes.yaml
mmmlu_ja_jp_moral_scenarios.yaml
mmmlu_ja_jp_nutrition.yaml
mmmlu_ja_jp_philosophy.yaml
mmmlu_ja_jp_prehistory.yaml
mmmlu_ja_jp_professional_accounting.yaml
mmmlu_ja_jp_professional_law.yaml
mmmlu_ja_jp_professional_medicine.yaml
mmmlu_ja_jp_professional_psychology.yaml
mmmlu_ja_jp_public_relations.yaml
mmmlu_ja_jp_security_studies.yaml
mmmlu_ja_jp_sociology.yaml
mmmlu_ja_jp_us_foreign_policy.yaml
mmmlu_ja_jp_virology.yaml
mmmlu_ja_jp_world_religions.yaml
mmmlu_ko_kr_abstract_algebra.yaml
mmmlu_ko_kr_anatomy.yaml
mmmlu_ko_kr_astronomy.yaml
mmmlu_ko_kr_business_ethics.yaml
mmmlu_ko_kr_clinical_knowledge.yaml
mmmlu_ko_kr_college_biology.yaml
mmmlu_ko_kr_college_chemistry.yaml
mmmlu_ko_kr_college_computer_science.yaml
mmmlu_ko_kr_college_mathematics.yaml
mmmlu_ko_kr_college_medicine.yaml
mmmlu_ko_kr_college_physics.yaml
mmmlu_ko_kr_computer_security.yaml
mmmlu_ko_kr_conceptual_physics.yaml
mmmlu_ko_kr_econometrics.yaml
mmmlu_ko_kr_electrical_engineering.yaml
mmmlu_ko_kr_elementary_mathematics.yaml
mmmlu_ko_kr_formal_logic.yaml
mmmlu_ko_kr_global_facts.yaml
mmmlu_ko_kr_high_school_biology.yaml
mmmlu_ko_kr_high_school_chemistry.yaml
mmmlu_ko_kr_high_school_computer_science.yaml
mmmlu_ko_kr_high_school_european_history.yaml
mmmlu_ko_kr_high_school_geography.yaml
mmmlu_ko_kr_high_school_government_and_politics.yaml
mmmlu_ko_kr_high_school_macroeconomics.yaml
mmmlu_ko_kr_high_school_mathematics.yaml
mmmlu_ko_kr_high_school_microeconomics.yaml
mmmlu_ko_kr_high_school_physics.yaml
mmmlu_ko_kr_high_school_psychology.yaml
mmmlu_ko_kr_high_school_statistics.yaml
mmmlu_ko_kr_high_school_us_history.yaml
mmmlu_ko_kr_high_school_world_history.yaml
mmmlu_ko_kr_human_aging.yaml
mmmlu_ko_kr_human_sexuality.yaml
mmmlu_ko_kr_international_law.yaml
mmmlu_ko_kr_jurisprudence.yaml
mmmlu_ko_kr_logical_fallacies.yaml
mmmlu_ko_kr_machine_learning.yaml
mmmlu_ko_kr_management.yaml
mmmlu_ko_kr_marketing.yaml
mmmlu_ko_kr_medical_genetics.yaml
mmmlu_ko_kr_miscellaneous.yaml
mmmlu_ko_kr_moral_disputes.yaml
mmmlu_ko_kr_moral_scenarios.yaml
mmmlu_ko_kr_nutrition.yaml
mmmlu_ko_kr_philosophy.yaml
mmmlu_ko_kr_prehistory.yaml
mmmlu_ko_kr_professional_accounting.yaml
mmmlu_ko_kr_professional_law.yaml
mmmlu_ko_kr_professional_medicine.yaml
mmmlu_ko_kr_professional_psychology.yaml
mmmlu_ko_kr_public_relations.yaml
mmmlu_ko_kr_security_studies.yaml
mmmlu_ko_kr_sociology.yaml
mmmlu_ko_kr_us_foreign_policy.yaml
mmmlu_ko_kr_virology.yaml
mmmlu_ko_kr_world_religions.yaml
mmmlu_pt_br_abstract_algebra.yaml
mmmlu_pt_br_anatomy.yaml
mmmlu_pt_br_astronomy.yaml
mmmlu_pt_br_business_ethics.yaml
mmmlu_pt_br_clinical_knowledge.yaml
mmmlu_pt_br_college_biology.yaml
mmmlu_pt_br_college_chemistry.yaml
mmmlu_pt_br_college_computer_science.yaml
mmmlu_pt_br_college_mathematics.yaml
mmmlu_pt_br_college_medicine.yaml
mmmlu_pt_br_college_physics.yaml
mmmlu_pt_br_computer_security.yaml
mmmlu_pt_br_conceptual_physics.yaml
mmmlu_pt_br_econometrics.yaml
mmmlu_pt_br_electrical_engineering.yaml
mmmlu_pt_br_elementary_mathematics.yaml
mmmlu_pt_br_formal_logic.yaml
mmmlu_pt_br_global_facts.yaml
mmmlu_pt_br_high_school_biology.yaml
mmmlu_pt_br_high_school_chemistry.yaml
mmmlu_pt_br_high_school_computer_science.yaml
mmmlu_pt_br_high_school_european_history.yaml
mmmlu_pt_br_high_school_geography.yaml
mmmlu_pt_br_high_school_government_and_politics.yaml
mmmlu_pt_br_high_school_macroeconomics.yaml
mmmlu_pt_br_high_school_mathematics.yaml
mmmlu_pt_br_high_school_microeconomics.yaml
mmmlu_pt_br_high_school_physics.yaml
mmmlu_pt_br_high_school_psychology.yaml
mmmlu_pt_br_high_school_statistics.yaml
mmmlu_pt_br_high_school_us_history.yaml
mmmlu_pt_br_high_school_world_history.yaml
mmmlu_pt_br_human_aging.yaml
mmmlu_pt_br_human_sexuality.yaml
mmmlu_pt_br_international_law.yaml
mmmlu_pt_br_jurisprudence.yaml
mmmlu_pt_br_logical_fallacies.yaml
mmmlu_pt_br_machine_learning.yaml
mmmlu_pt_br_management.yaml
mmmlu_pt_br_marketing.yaml
mmmlu_pt_br_medical_genetics.yaml
mmmlu_pt_br_miscellaneous.yaml
mmmlu_pt_br_moral_disputes.yaml
mmmlu_pt_br_moral_scenarios.yaml
mmmlu_pt_br_nutrition.yaml
mmmlu_pt_br_philosophy.yaml
mmmlu_pt_br_prehistory.yaml
mmmlu_pt_br_professional_accounting.yaml
mmmlu_pt_br_professional_law.yaml
mmmlu_pt_br_professional_medicine.yaml
mmmlu_pt_br_professional_psychology.yaml
mmmlu_pt_br_public_relations.yaml
mmmlu_pt_br_security_studies.yaml
mmmlu_pt_br_sociology.yaml
mmmlu_pt_br_us_foreign_policy.yaml
mmmlu_pt_br_virology.yaml
mmmlu_pt_br_world_religions.yaml
mmmlu_sw_ke_abstract_algebra.yaml
mmmlu_sw_ke_anatomy.yaml
mmmlu_sw_ke_astronomy.yaml
mmmlu_sw_ke_business_ethics.yaml
mmmlu_sw_ke_clinical_knowledge.yaml
mmmlu_sw_ke_college_biology.yaml
mmmlu_sw_ke_college_chemistry.yaml
mmmlu_sw_ke_college_computer_science.yaml
mmmlu_sw_ke_college_mathematics.yaml
mmmlu_sw_ke_college_medicine.yaml
mmmlu_sw_ke_college_physics.yaml
mmmlu_sw_ke_computer_security.yaml
mmmlu_sw_ke_conceptual_physics.yaml
mmmlu_sw_ke_econometrics.yaml
mmmlu_sw_ke_electrical_engineering.yaml
mmmlu_sw_ke_elementary_mathematics.yaml
mmmlu_sw_ke_formal_logic.yaml
mmmlu_sw_ke_global_facts.yaml
mmmlu_sw_ke_high_school_biology.yaml
mmmlu_sw_ke_high_school_chemistry.yaml
mmmlu_sw_ke_high_school_computer_science.yaml
mmmlu_sw_ke_high_school_european_history.yaml
mmmlu_sw_ke_high_school_geography.yaml
mmmlu_sw_ke_high_school_government_and_politics.yaml
mmmlu_sw_ke_high_school_macroeconomics.yaml
mmmlu_sw_ke_high_school_mathematics.yaml
mmmlu_sw_ke_high_school_microeconomics.yaml
mmmlu_sw_ke_high_school_physics.yaml
mmmlu_sw_ke_high_school_psychology.yaml
mmmlu_sw_ke_high_school_statistics.yaml
mmmlu_sw_ke_high_school_us_history.yaml
mmmlu_sw_ke_high_school_world_history.yaml
mmmlu_sw_ke_human_aging.yaml
mmmlu_sw_ke_human_sexuality.yaml
mmmlu_sw_ke_international_law.yaml
mmmlu_sw_ke_jurisprudence.yaml
mmmlu_sw_ke_logical_fallacies.yaml
mmmlu_sw_ke_machine_learning.yaml
mmmlu_sw_ke_management.yaml
mmmlu_sw_ke_marketing.yaml
mmmlu_sw_ke_medical_genetics.yaml
mmmlu_sw_ke_miscellaneous.yaml
mmmlu_sw_ke_moral_disputes.yaml
mmmlu_sw_ke_moral_scenarios.yaml
mmmlu_sw_ke_nutrition.yaml
mmmlu_sw_ke_philosophy.yaml
mmmlu_sw_ke_prehistory.yaml
mmmlu_sw_ke_professional_accounting.yaml
mmmlu_sw_ke_professional_law.yaml
mmmlu_sw_ke_professional_medicine.yaml
mmmlu_sw_ke_professional_psychology.yaml
mmmlu_sw_ke_public_relations.yaml
mmmlu_sw_ke_security_studies.yaml
mmmlu_sw_ke_sociology.yaml
mmmlu_sw_ke_us_foreign_policy.yaml
mmmlu_sw_ke_virology.yaml
mmmlu_sw_ke_world_religions.yaml
mmmlu_yo_ng_abstract_algebra.yaml
mmmlu_yo_ng_anatomy.yaml
mmmlu_yo_ng_astronomy.yaml
mmmlu_yo_ng_business_ethics.yaml
mmmlu_yo_ng_clinical_knowledge.yaml
mmmlu_yo_ng_college_biology.yaml
mmmlu_yo_ng_college_chemistry.yaml
mmmlu_yo_ng_college_computer_science.yaml
mmmlu_yo_ng_college_mathematics.yaml
mmmlu_yo_ng_college_medicine.yaml
mmmlu_yo_ng_college_physics.yaml
mmmlu_yo_ng_computer_security.yaml
mmmlu_yo_ng_conceptual_physics.yaml
mmmlu_yo_ng_econometrics.yaml
mmmlu_yo_ng_electrical_engineering.yaml
mmmlu_yo_ng_elementary_mathematics.yaml
mmmlu_yo_ng_formal_logic.yaml
mmmlu_yo_ng_global_facts.yaml
mmmlu_yo_ng_high_school_biology.yaml
mmmlu_yo_ng_high_school_chemistry.yaml
mmmlu_yo_ng_high_school_computer_science.yaml
mmmlu_yo_ng_high_school_european_history.yaml
mmmlu_yo_ng_high_school_geography.yaml
mmmlu_yo_ng_high_school_government_and_politics.yaml
mmmlu_yo_ng_high_school_macroeconomics.yaml
mmmlu_yo_ng_high_school_mathematics.yaml
mmmlu_yo_ng_high_school_microeconomics.yaml
mmmlu_yo_ng_high_school_physics.yaml
mmmlu_yo_ng_high_school_psychology.yaml
mmmlu_yo_ng_high_school_statistics.yaml
mmmlu_yo_ng_high_school_us_history.yaml
mmmlu_yo_ng_high_school_world_history.yaml
mmmlu_yo_ng_human_aging.yaml
mmmlu_yo_ng_human_sexuality.yaml
mmmlu_yo_ng_international_law.yaml
mmmlu_yo_ng_jurisprudence.yaml
mmmlu_yo_ng_logical_fallacies.yaml
mmmlu_yo_ng_machine_learning.yaml
mmmlu_yo_ng_management.yaml
mmmlu_yo_ng_marketing.yaml
mmmlu_yo_ng_medical_genetics.yaml
mmmlu_yo_ng_miscellaneous.yaml
mmmlu_yo_ng_moral_disputes.yaml
mmmlu_yo_ng_moral_scenarios.yaml
mmmlu_yo_ng_nutrition.yaml
mmmlu_yo_ng_philosophy.yaml
mmmlu_yo_ng_prehistory.yaml
mmmlu_yo_ng_professional_accounting.yaml
mmmlu_yo_ng_professional_law.yaml
mmmlu_yo_ng_professional_medicine.yaml
mmmlu_yo_ng_professional_psychology.yaml
mmmlu_yo_ng_public_relations.yaml
mmmlu_yo_ng_security_studies.yaml
mmmlu_yo_ng_sociology.yaml
mmmlu_yo_ng_us_foreign_policy.yaml
mmmlu_yo_ng_virology.yaml
mmmlu_yo_ng_world_religions.yaml
mmmlu_zh_cn_abstract_algebra.yaml
mmmlu_zh_cn_anatomy.yaml
mmmlu_zh_cn_astronomy.yaml
mmmlu_zh_cn_business_ethics.yaml
mmmlu_zh_cn_clinical_knowledge.yaml
mmmlu_zh_cn_college_biology.yaml
mmmlu_zh_cn_college_chemistry.yaml
mmmlu_zh_cn_college_computer_science.yaml
mmmlu_zh_cn_college_mathematics.yaml
mmmlu_zh_cn_college_medicine.yaml
mmmlu_zh_cn_college_physics.yaml
mmmlu_zh_cn_computer_security.yaml
mmmlu_zh_cn_conceptual_physics.yaml
mmmlu_zh_cn_econometrics.yaml
mmmlu_zh_cn_electrical_engineering.yaml
mmmlu_zh_cn_elementary_mathematics.yaml
mmmlu_zh_cn_formal_logic.yaml
mmmlu_zh_cn_global_facts.yaml
mmmlu_zh_cn_high_school_biology.yaml
mmmlu_zh_cn_high_school_chemistry.yaml
mmmlu_zh_cn_high_school_computer_science.yaml
mmmlu_zh_cn_high_school_european_history.yaml
mmmlu_zh_cn_high_school_geography.yaml
mmmlu_zh_cn_high_school_government_and_politics.yaml
mmmlu_zh_cn_high_school_macroeconomics.yaml
mmmlu_zh_cn_high_school_mathematics.yaml
mmmlu_zh_cn_high_school_microeconomics.yaml
mmmlu_zh_cn_high_school_physics.yaml
mmmlu_zh_cn_high_school_psychology.yaml
mmmlu_zh_cn_high_school_statistics.yaml
mmmlu_zh_cn_high_school_us_history.yaml
mmmlu_zh_cn_high_school_world_history.yaml
mmmlu_zh_cn_human_aging.yaml
mmmlu_zh_cn_human_sexuality.yaml
mmmlu_zh_cn_international_law.yaml
mmmlu_zh_cn_jurisprudence.yaml
mmmlu_zh_cn_logical_fallacies.yaml
mmmlu_zh_cn_machine_learning.yaml
mmmlu_zh_cn_management.yaml
mmmlu_zh_cn_marketing.yaml
mmmlu_zh_cn_medical_genetics.yaml
mmmlu_zh_cn_miscellaneous.yaml
mmmlu_zh_cn_moral_disputes.yaml
mmmlu_zh_cn_moral_scenarios.yaml
mmmlu_zh_cn_nutrition.yaml
mmmlu_zh_cn_philosophy.yaml
mmmlu_zh_cn_prehistory.yaml
mmmlu_zh_cn_professional_accounting.yaml
mmmlu_zh_cn_professional_law.yaml
mmmlu_zh_cn_professional_medicine.yaml
mmmlu_zh_cn_professional_psychology.yaml
mmmlu_zh_cn_public_relations.yaml
mmmlu_zh_cn_security_studies.yaml
mmmlu_zh_cn_sociology.yaml
mmmlu_zh_cn_us_foreign_policy.yaml
mmmlu_zh_cn_virology.yaml
mmmlu_zh_cn_world_religions.yaml
utils.py