From 9c71cfece5d954ff70d296bfceb5fa783f45c1b0 Mon Sep 17 00:00:00 2001 From: WangRongsheng Date: Wed, 31 Jan 2024 00:15:44 +0800 Subject: [PATCH] update ENFJ and ISFP --- results/ENFJ.csv | 508 ++++++++++++++++++++++++----------------------- results/ISFP.csv | 497 ++++++++++++++++++++++++---------------------- 2 files changed, 510 insertions(+), 495 deletions(-) diff --git a/results/ENFJ.csv b/results/ENFJ.csv index 344f8cb..06910e7 100644 --- a/results/ENFJ.csv +++ b/results/ENFJ.csv @@ -1,253 +1,255 @@ -dataset,version,metric,mode,opencompass.models.huggingface.HuggingFace_FarReelAILab_Machine_Mindset_en_ENFJ -GaokaoBench_2010-2022_Math_II_MCQs,5b0b29,score,gen,16.06 -GaokaoBench_2010-2022_Math_I_MCQs,5b0b29,score,gen,15.89 -GaokaoBench_2010-2022_History_MCQs,3613b5,score,gen,11.85 -GaokaoBench_2010-2022_Biology_MCQs,d26e80,score,gen,17.33 -GaokaoBench_2010-2022_Political_Science_MCQs,70fce9,score,gen,8.12 -GaokaoBench_2010-2022_Physics_MCQs,8a0c30,score,gen,2.34 -GaokaoBench_2010-2022_Chemistry_MCQs,852bbd,score,gen,14.52 -GaokaoBench_2010-2013_English_MCQs,01b50f,score,gen,15.24 -GaokaoBench_2010-2022_Chinese_Modern_Lit,e19c31,score,gen,1.15 -GaokaoBench_2010-2022_English_Fill_in_Blanks,924021,score,gen,12.67 -GaokaoBench_2012-2022_English_Cloze_Test,11f6ce,score,gen,0.77 -GaokaoBench_2010-2022_Geography_MCQs,862192,score,gen,10.53 -GaokaoBench_2010-2022_English_Reading_Comp,ffdef4,score,gen,4.26 -GaokaoBench_2010-2022_Chinese_Lang_and_Usage_MCQs,ba10b2,score,gen,7.5 -GaokaoBench_2010-2022_Math_I_Fill-in-the-Blank,9dd6c7,score,gen,0 -GaokaoBench_2010-2022_Math_II_Fill-in-the-Blank,9dd6c7,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Famous_Passages_and_Sentences_Dictation,58053d,score,gen,0 -GaokaoBench_2014-2022_English_Language_Cloze_Passage,d431f7,score,gen,0 -GaokaoBench_2010-2022_Geography_Open-ended_Questions,475d13,score,gen,0 -GaokaoBench_2010-2022_Chemistry_Open-ended_Questions,0bccc3,score,gen,0 -GaokaoBench_2010-2022_Math_I_Open-ended_Questions,8a0cf5,score,gen,0 -GaokaoBench_2010-2022_History_Open-ended_Questions,9fbad8,score,gen,0 -GaokaoBench_2010-2022_Biology_Open-ended_Questions,e0cb29,score,gen,0 -GaokaoBench_2010-2022_Math_II_Open-ended_Questions,8a0cf5,score,gen,0 -GaokaoBench_2010-2022_Physics_Open-ended_Questions,423d19,score,gen,0 -GaokaoBench_2010-2022_Political_Science_Open-ended_Questions,0eee0a,score,gen,0 -GaokaoBench_2012-2022_English_Language_Error_Correction,6a3cae,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Ancient_Poetry_Reading,ee6cc7,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Practical_Text_Reading,4dea5a,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Literary_Text_Reading,979d8b,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Classical_Chinese_Reading,9de717,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Language_and_Writing_Skills_Open-ended_Questions,d2ed84,score,gen,0 -agieval-gaokao-chinese,774562,accuracy,gen,4.47 -agieval-gaokao-english,cb5bc6,accuracy,gen,5.23 -agieval-gaokao-geography,2ca56f,accuracy,gen,4.02 -agieval-gaokao-history,9c3ae0,accuracy,gen,4.68 -agieval-gaokao-biology,277c85,accuracy,gen,9.05 -agieval-gaokao-chemistry,d62fd4,accuracy,gen,6.28 -agieval-gaokao-mathqa,e2ea74,accuracy,gen,5.7 -agieval-logiqa-zh,03474d,accuracy,gen,10.29 -agieval-lsat-ar,ed1edf,accuracy,gen,0.43 -agieval-lsat-lr,ec6882,accuracy,gen,1.76 -agieval-lsat-rc,33077d,accuracy,gen,2.6 -agieval-logiqa-en,c6ee60,accuracy,gen,1.54 -agieval-sat-math,6c970d,accuracy,gen,2.73 -agieval-sat-en,4e3fef,accuracy,gen,9.71 -agieval-sat-en-without-passage,4e3fef,accuracy,gen,2.43 -agieval-aqua-rat,c090ca,accuracy,gen,0.39 -agieval-gaokao-physics,7.70E+06,accuracy,gen,11.5 -agieval-jec-qa-kd,-,-,-,- -agieval-jec-qa-ca,47bc29,accuracy,gen,6.1 -agieval-gaokao-mathcloze,b2c3c3,score,gen,0 -agieval-math,e0c6d9,score,gen,0.4 -ceval-computer_network,db9ce2,accuracy,gen,31.58 -ceval-operating_system,1c2571,accuracy,gen,31.58 -ceval-computer_architecture,a74dad,accuracy,gen,28.57 -ceval-college_programming,4ca32a,accuracy,gen,29.73 -ceval-college_physics,963fa8,accuracy,gen,5.26 -ceval-college_chemistry,e78857,accuracy,gen,20.83 -ceval-advanced_mathematics,ce03e2,accuracy,gen,21.05 -ceval-probability_and_statistics,65e812,accuracy,gen,27.78 -ceval-discrete_mathematics,e894ae,accuracy,gen,37.5 -ceval-electrical_engineer,ae42b9,accuracy,gen,35.14 -ceval-metrology_engineer,ee34ea,accuracy,gen,33.33 -ceval-high_school_mathematics,1dc5bf,accuracy,gen,44.44 -ceval-high_school_physics,adf25f,accuracy,gen,31.58 -ceval-high_school_chemistry,2ed27f,accuracy,gen,42.11 -ceval-high_school_biology,8e2b9a,accuracy,gen,15.79 -ceval-middle_school_mathematics,bee8d5,accuracy,gen,47.37 -ceval-middle_school_biology,86817c,accuracy,gen,23.81 -ceval-middle_school_physics,8accf6,accuracy,gen,31.58 -ceval-middle_school_chemistry,167a15,accuracy,gen,35 -ceval-veterinary_medicine,b4e08d,accuracy,gen,21.74 -ceval-college_economics,f3f4e6,accuracy,gen,27.27 -ceval-business_administration,c1614e,accuracy,gen,24.24 -ceval-marxism,cf874c,accuracy,gen,21.05 -ceval-mao_zedong_thought,51c7a4,accuracy,gen,33.33 -ceval-education_science,591fee,accuracy,gen,24.14 -ceval-teacher_qualification,4e4ced,accuracy,gen,29.55 -ceval-high_school_politics,5c0de2,accuracy,gen,21.05 -ceval-high_school_geography,865461,accuracy,gen,26.32 -ceval-middle_school_politics,5be3e7,accuracy,gen,33.33 -ceval-middle_school_geography,8a63be,accuracy,gen,50 -ceval-modern_chinese_history,fc01af,accuracy,gen,39.13 -ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,42.11 -ceval-logic,f5b022,accuracy,gen,22.73 -ceval-law,a110a1,accuracy,gen,33.33 -ceval-chinese_language_and_literature,0f8b68,accuracy,gen,17.39 -ceval-art_studies,2a1300,accuracy,gen,18.18 -ceval-professional_tour_guide,4e673e,accuracy,gen,24.14 -ceval-legal_professional,ce8787,accuracy,gen,30.43 -ceval-high_school_chinese,315705,accuracy,gen,10.53 -ceval-high_school_history,7eb30a,accuracy,gen,30 -ceval-middle_school_history,48ab4a,accuracy,gen,22.73 -ceval-civil_servant,87d061,accuracy,gen,25.53 -ceval-sports_science,70f27b,accuracy,gen,31.58 -ceval-plant_protection,8941f9,accuracy,gen,45.45 -ceval-basic_medicine,c409d6,accuracy,gen,47.37 -ceval-clinical_medicine,49e82d,accuracy,gen,27.27 -ceval-urban_and_rural_planner,95b885,accuracy,gen,30.43 -ceval-accountant,2837,accuracy,gen,26.53 -ceval-fire_engineer,bc23f5,accuracy,gen,29.03 -ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,29.03 -ceval-tax_accountant,3a5e3c,accuracy,gen,22.45 -ceval-physician,6e277d,accuracy,gen,32.65 -cmmlu-agronomy,4c7f2c,accuracy,gen,17.75 -cmmlu-anatomy,ea09bf,accuracy,gen,24.32 -cmmlu-ancient_chinese,f7c97f,accuracy,gen,21.95 -cmmlu-arts,dd77b8,accuracy,gen,22.5 -cmmlu-astronomy,1e49db,accuracy,gen,9.7 -cmmlu-business_ethics,dc78cb,accuracy,gen,25.36 -cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,13.12 -cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,18.32 -cmmlu-chinese_food_culture,2d568a,accuracy,gen,19.85 -cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,16.82 -cmmlu-chinese_history,4cc7ed,accuracy,gen,8.05 -cmmlu-chinese_literature,af3c41,accuracy,gen,2.45 -cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,16.2 -cmmlu-clinical_knowledge,c55b1d,accuracy,gen,11.81 -cmmlu-college_actuarial_science,d3c360,accuracy,gen,4.72 -cmmlu-college_education,df8790,accuracy,gen,25.23 -cmmlu-college_engineering_hydrology,673f23,accuracy,gen,22.64 -cmmlu-college_law,524c3a,accuracy,gen,17.59 -cmmlu-college_mathematics,e4ebad,accuracy,gen,7.62 -cmmlu-college_medical_statistics,55af35,accuracy,gen,14.15 -cmmlu-college_medicine,702f48,accuracy,gen,20.51 -cmmlu-computer_science,637007,accuracy,gen,20.59 -cmmlu-computer_security,932b6b,accuracy,gen,19.3 -cmmlu-conceptual_physics,cfc077,accuracy,gen,17.69 -cmmlu-construction_project_management,968a4a,accuracy,gen,20.14 -cmmlu-economics,ddaf7c,accuracy,gen,21.38 -cmmlu-education,c35963,accuracy,gen,13.5 -cmmlu-electrical_engineering,70e98a,accuracy,gen,20.35 -cmmlu-elementary_chinese,cbcd6a,accuracy,gen,24.21 -cmmlu-elementary_commonsense,a67f37,accuracy,gen,24.24 -cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,5.88 -cmmlu-elementary_mathematics,a9d403,accuracy,gen,25.65 -cmmlu-ethnology,31955f,accuracy,gen,17.04 -cmmlu-food_science,741d8e,accuracy,gen,23.08 -cmmlu-genetics,c326f7,accuracy,gen,10.8 -cmmlu-global_facts,0a1236,accuracy,gen,14.09 -cmmlu-high_school_biology,2be811,accuracy,gen,6.51 -cmmlu-high_school_chemistry,d63c05,accuracy,gen,19.7 -cmmlu-high_school_geography,5cd489,accuracy,gen,18.64 -cmmlu-high_school_mathematics,6b2087,accuracy,gen,21.34 -cmmlu-high_school_physics,3df353,accuracy,gen,10 -cmmlu-high_school_politics,7a88d8,accuracy,gen,9.09 -cmmlu-human_sexuality,54ac98,accuracy,gen,17.46 -cmmlu-international_law,0f5d40,accuracy,gen,12.43 -cmmlu-journalism,a4f6a0,accuracy,gen,23.84 -cmmlu-jurisprudence,7843da,accuracy,gen,22.38 -cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,21.03 -cmmlu-logical,15a71b,accuracy,gen,14.63 -cmmlu-machine_learning,bc6ad4,accuracy,gen,4.92 -cmmlu-management,e5e8db,accuracy,gen,19.05 -cmmlu-marketing,8b4c18,accuracy,gen,12.78 -cmmlu-marxist_theory,75eb79,accuracy,gen,23.28 -cmmlu-modern_chinese,83a9b7,accuracy,gen,23.28 -cmmlu-nutrition,adfff7,accuracy,gen,22.07 -cmmlu-philosophy,75e22d,accuracy,gen,20.95 -cmmlu-professional_accounting,0edc91,accuracy,gen,24.57 -cmmlu-professional_law,d24af5,accuracy,gen,17.06 -cmmlu-professional_medicine,134139,accuracy,gen,18.62 -cmmlu-professional_psychology,ec920e,accuracy,gen,18.97 -cmmlu-public_relations,70ee06,accuracy,gen,6.32 -cmmlu-security_study,45f96f,accuracy,gen,22.96 -cmmlu-sociology,485285,accuracy,gen,24.34 -cmmlu-sports_science,838cfe,accuracy,gen,18.79 -cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,19.46 -cmmlu-virology,8925bf,accuracy,gen,20.71 -cmmlu-world_history,57c97c,accuracy,gen,3.11 -cmmlu-world_religions,1d0f4b,accuracy,gen,20.62 -gsm8k,-,-,-,- -math,265cce,accuracy,gen,0.2 -lukaemon_mmlu_college_biology,8c2e29,accuracy,gen,1.39 -lukaemon_mmlu_college_chemistry,0afccd,accuracy,gen,6 -lukaemon_mmlu_college_computer_science,c1c1b4,accuracy,gen,3 -lukaemon_mmlu_college_mathematics,9deed0,accuracy,gen,3 -lukaemon_mmlu_college_physics,f5cf5e,accuracy,gen,1.96 -lukaemon_mmlu_electrical_engineering,3d694d,accuracy,gen,3.45 -lukaemon_mmlu_astronomy,7ef16f,accuracy,gen,0.66 -lukaemon_mmlu_anatomy,2d597d,accuracy,gen,2.22 -lukaemon_mmlu_abstract_algebra,ec092c,accuracy,gen,2 -lukaemon_mmlu_machine_learning,d489ae,accuracy,gen,3.57 -lukaemon_mmlu_clinical_knowledge,af10df,accuracy,gen,1.51 -lukaemon_mmlu_global_facts,cad9e0,accuracy,gen,3 -lukaemon_mmlu_management,65f310,accuracy,gen,11.65 -lukaemon_mmlu_nutrition,80bf96,accuracy,gen,1.63 -lukaemon_mmlu_marketing,9a98c0,accuracy,gen,2.56 -lukaemon_mmlu_professional_accounting,9cc7e2,accuracy,gen,1.06 -lukaemon_mmlu_high_school_geography,c28a4c,accuracy,gen,2.02 -lukaemon_mmlu_international_law,408d4e,accuracy,gen,0.83 -lukaemon_mmlu_moral_scenarios,9f30a6,accuracy,gen,0 -lukaemon_mmlu_computer_security,2753c1,accuracy,gen,0 -lukaemon_mmlu_high_school_microeconomics,af9eae,accuracy,gen,0.84 -lukaemon_mmlu_professional_law,7c7a62,accuracy,gen,7.3 -lukaemon_mmlu_medical_genetics,b1a3a7,accuracy,gen,0 -lukaemon_mmlu_professional_psychology,c6b790,accuracy,gen,1.31 -lukaemon_mmlu_jurisprudence,f41074,accuracy,gen,0 -lukaemon_mmlu_world_religions,d44a95,accuracy,gen,2.34 -lukaemon_mmlu_philosophy,d36ef3,accuracy,gen,4.5 -lukaemon_mmlu_virology,0a5f8e,accuracy,gen,1.2 -lukaemon_mmlu_high_school_chemistry,5b2ef9,accuracy,gen,10.84 -lukaemon_mmlu_public_relations,4c7898,accuracy,gen,3.64 -lukaemon_mmlu_high_school_macroeconomics,3f841b,accuracy,gen,0 -lukaemon_mmlu_human_sexuality,4d1f3e,accuracy,gen,2.29 -lukaemon_mmlu_elementary_mathematics,0f5d3a,accuracy,gen,4.76 -lukaemon_mmlu_high_school_physics,0dd929,accuracy,gen,1.32 -lukaemon_mmlu_high_school_computer_science,bf31fd,accuracy,gen,15 -lukaemon_mmlu_high_school_european_history,d1b67e,accuracy,gen,3.03 -lukaemon_mmlu_business_ethics,af53f3,accuracy,gen,1 -lukaemon_mmlu_moral_disputes,48239e,accuracy,gen,1.16 -lukaemon_mmlu_high_school_statistics,47e18e,accuracy,gen,2.78 -lukaemon_mmlu_miscellaneous,573569,accuracy,gen,18.01 -lukaemon_mmlu_formal_logic,7a0414,accuracy,gen,12.7 -lukaemon_mmlu_high_school_government_and_politics,d907eb,accuracy,gen,0.52 -lukaemon_mmlu_prehistory,65aa94,accuracy,gen,1.85 -lukaemon_mmlu_security_studies,9ea7d3,accuracy,gen,0.41 -lukaemon_mmlu_high_school_biology,775183,accuracy,gen,1.61 -lukaemon_mmlu_logical_fallacies,19746a,accuracy,gen,1.84 -lukaemon_mmlu_high_school_world_history,6665dc,accuracy,gen,2.53 -lukaemon_mmlu_professional_medicine,a05bab,accuracy,gen,0.37 -lukaemon_mmlu_high_school_mathematics,0e6a7e,accuracy,gen,0.74 -lukaemon_mmlu_college_medicine,5215f1,accuracy,gen,1.73 -lukaemon_mmlu_high_school_us_history,b5f235,accuracy,gen,4.41 -lukaemon_mmlu_sociology,4980ec,accuracy,gen,0.5 -lukaemon_mmlu_econometrics,4d590b,accuracy,gen,18.42 -lukaemon_mmlu_high_school_psychology,4.40E+98,accuracy,gen,0.37 -lukaemon_mmlu_human_aging,d0a8e1,accuracy,gen,2.24 -lukaemon_mmlu_us_foreign_policy,adcc88,accuracy,gen,0 -lukaemon_mmlu_conceptual_physics,a111d3,accuracy,gen,2.13 -agieval-english,-,naive_average,gen,2.44 -agieval-gaokao,-,naive_average,gen,5.66 -mmlu-humanities,-,naive_average,gen,3.27 -mmlu-stem,-,naive_average,gen,3.5 -mmlu-social-science,-,naive_average,gen,2.53 -mmlu-other,-,naive_average,gen,3.54 -mmlu,-,naive_average,gen,3.25 -mmlu-weighted,-,weighted_average,gen,3.7 -cmmlu-humanities,-,naive_average,gen,15.32 -cmmlu-stem,-,naive_average,gen,15.38 -cmmlu-social-science,-,naive_average,gen,19.02 -cmmlu-other,-,naive_average,gen,18.56 -cmmlu-china-specific,-,naive_average,gen,16.95 -cmmlu,-,naive_average,gen,17.28 -ceval-stem,-,naive_average,gen,29.79 -ceval-social-science,-,naive_average,gen,29.03 -ceval-humanities,-,naive_average,gen,26.43 -ceval-other,-,naive_average,gen,31.58 -ceval-hard,-,naive_average,gen,28.82 -ceval,-,naive_average,gen,29.31 -GaokaoBench,-,weighted_average,gen,11.25 +dataset,version,metric,mode,opencompass.models.huggingface.HuggingFace_FarReelAILab_Machine_Mindset_en_ENFJ +GaokaoBench_2010-2022_Math_II_MCQs,5b0b29,score,gen,16.06 +GaokaoBench_2010-2022_Math_I_MCQs,5b0b29,score,gen,15.89 +GaokaoBench_2010-2022_History_MCQs,3613b5,score,gen,11.85 +GaokaoBench_2010-2022_Biology_MCQs,d26e80,score,gen,17.33 +GaokaoBench_2010-2022_Political_Science_MCQs,70fce9,score,gen,8.12 +GaokaoBench_2010-2022_Physics_MCQs,8a0c30,score,gen,2.34 +GaokaoBench_2010-2022_Chemistry_MCQs,852bbd,score,gen,14.52 +GaokaoBench_2010-2013_English_MCQs,01b50f,score,gen,15.24 +GaokaoBench_2010-2022_Chinese_Modern_Lit,e19c31,score,gen,1.15 +GaokaoBench_2010-2022_English_Fill_in_Blanks,924021,score,gen,12.67 +GaokaoBench_2012-2022_English_Cloze_Test,11f6ce,score,gen,0.77 +GaokaoBench_2010-2022_Geography_MCQs,862192,score,gen,10.53 +GaokaoBench_2010-2022_English_Reading_Comp,ffdef4,score,gen,4.26 +GaokaoBench_2010-2022_Chinese_Lang_and_Usage_MCQs,ba10b2,score,gen,7.50 +GaokaoBench_2010-2022_Math_I_Fill-in-the-Blank,9dd6c7,score,gen,0.00 +GaokaoBench_2010-2022_Math_II_Fill-in-the-Blank,9dd6c7,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Famous_Passages_and_Sentences_Dictation,58053d,score,gen,0.00 +GaokaoBench_2014-2022_English_Language_Cloze_Passage,d431f7,score,gen,0.00 +GaokaoBench_2010-2022_Geography_Open-ended_Questions,475d13,score,gen,0.00 +GaokaoBench_2010-2022_Chemistry_Open-ended_Questions,0bccc3,score,gen,0.00 +GaokaoBench_2010-2022_Math_I_Open-ended_Questions,8a0cf5,score,gen,0.00 +GaokaoBench_2010-2022_History_Open-ended_Questions,9fbad8,score,gen,0.00 +GaokaoBench_2010-2022_Biology_Open-ended_Questions,e0cb29,score,gen,0.00 +GaokaoBench_2010-2022_Math_II_Open-ended_Questions,8a0cf5,score,gen,0.00 +GaokaoBench_2010-2022_Physics_Open-ended_Questions,423d19,score,gen,0.00 +GaokaoBench_2010-2022_Political_Science_Open-ended_Questions,0eee0a,score,gen,0.00 +GaokaoBench_2012-2022_English_Language_Error_Correction,6a3cae,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Ancient_Poetry_Reading,ee6cc7,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Practical_Text_Reading,4dea5a,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Literary_Text_Reading,979d8b,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Classical_Chinese_Reading,9de717,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Language_and_Writing_Skills_Open-ended_Questions,d2ed84,score,gen,0.00 +agieval-gaokao-chinese,774562,accuracy,gen,4.47 +agieval-gaokao-english,cb5bc6,accuracy,gen,5.23 +agieval-gaokao-geography,2ca56f,accuracy,gen,4.02 +agieval-gaokao-history,9c3ae0,accuracy,gen,4.68 +agieval-gaokao-biology,277c85,accuracy,gen,9.05 +agieval-gaokao-chemistry,d62fd4,accuracy,gen,6.28 +agieval-gaokao-mathqa,e2ea74,accuracy,gen,5.70 +agieval-logiqa-zh,03474d,accuracy,gen,10.29 +agieval-lsat-ar,ed1edf,accuracy,gen,0.43 +agieval-lsat-lr,ec6882,accuracy,gen,1.76 +agieval-lsat-rc,33077d,accuracy,gen,2.60 +agieval-logiqa-en,c6ee60,accuracy,gen,1.54 +agieval-sat-math,6c970d,accuracy,gen,2.73 +agieval-sat-en,4e3fef,accuracy,gen,9.71 +agieval-sat-en-without-passage,4e3fef,accuracy,gen,2.43 +agieval-aqua-rat,c090ca,accuracy,gen,0.39 +agieval-gaokao-physics,7704e3,accuracy,gen,11.50 +agieval-jec-qa-kd,b1e586,accuracy,gen,4.10 +agieval-jec-qa-ca,47bc29,accuracy,gen,6.10 +agieval-gaokao-mathcloze,b2c3c3,score,gen,0.00 +agieval-math,e0c6d9,score,gen,0.40 +ceval-computer_network,db9ce2,accuracy,gen,31.58 +ceval-operating_system,1c2571,accuracy,gen,31.58 +ceval-computer_architecture,a74dad,accuracy,gen,28.57 +ceval-college_programming,4ca32a,accuracy,gen,29.73 +ceval-college_physics,963fa8,accuracy,gen,5.26 +ceval-college_chemistry,e78857,accuracy,gen,20.83 +ceval-advanced_mathematics,ce03e2,accuracy,gen,21.05 +ceval-probability_and_statistics,65e812,accuracy,gen,27.78 +ceval-discrete_mathematics,e894ae,accuracy,gen,37.50 +ceval-electrical_engineer,ae42b9,accuracy,gen,35.14 +ceval-metrology_engineer,ee34ea,accuracy,gen,33.33 +ceval-high_school_mathematics,1dc5bf,accuracy,gen,44.44 +ceval-high_school_physics,adf25f,accuracy,gen,31.58 +ceval-high_school_chemistry,2ed27f,accuracy,gen,42.11 +ceval-high_school_biology,8e2b9a,accuracy,gen,15.79 +ceval-middle_school_mathematics,bee8d5,accuracy,gen,47.37 +ceval-middle_school_biology,86817c,accuracy,gen,23.81 +ceval-middle_school_physics,8accf6,accuracy,gen,31.58 +ceval-middle_school_chemistry,167a15,accuracy,gen,35.00 +ceval-veterinary_medicine,b4e08d,accuracy,gen,21.74 +ceval-college_economics,f3f4e6,accuracy,gen,27.27 +ceval-business_administration,c1614e,accuracy,gen,24.24 +ceval-marxism,cf874c,accuracy,gen,21.05 +ceval-mao_zedong_thought,51c7a4,accuracy,gen,33.33 +ceval-education_science,591fee,accuracy,gen,24.14 +ceval-teacher_qualification,4e4ced,accuracy,gen,29.55 +ceval-high_school_politics,5c0de2,accuracy,gen,21.05 +ceval-high_school_geography,865461,accuracy,gen,26.32 +ceval-middle_school_politics,5be3e7,accuracy,gen,33.33 +ceval-middle_school_geography,8a63be,accuracy,gen,50.00 +ceval-modern_chinese_history,fc01af,accuracy,gen,39.13 +ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,42.11 +ceval-logic,f5b022,accuracy,gen,22.73 +ceval-law,a110a1,accuracy,gen,33.33 +ceval-chinese_language_and_literature,0f8b68,accuracy,gen,17.39 +ceval-art_studies,2a1300,accuracy,gen,18.18 +ceval-professional_tour_guide,4e673e,accuracy,gen,24.14 +ceval-legal_professional,ce8787,accuracy,gen,30.43 +ceval-high_school_chinese,315705,accuracy,gen,10.53 +ceval-high_school_history,7eb30a,accuracy,gen,30.00 +ceval-middle_school_history,48ab4a,accuracy,gen,22.73 +ceval-civil_servant,87d061,accuracy,gen,25.53 +ceval-sports_science,70f27b,accuracy,gen,31.58 +ceval-plant_protection,8941f9,accuracy,gen,45.45 +ceval-basic_medicine,c409d6,accuracy,gen,47.37 +ceval-clinical_medicine,49e82d,accuracy,gen,27.27 +ceval-urban_and_rural_planner,95b885,accuracy,gen,30.43 +ceval-accountant,002837,accuracy,gen,26.53 +ceval-fire_engineer,bc23f5,accuracy,gen,29.03 +ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,29.03 +ceval-tax_accountant,3a5e3c,accuracy,gen,22.45 +ceval-physician,6e277d,accuracy,gen,32.65 +cmmlu-agronomy,4c7f2c,accuracy,gen,17.75 +cmmlu-anatomy,ea09bf,accuracy,gen,24.32 +cmmlu-ancient_chinese,f7c97f,accuracy,gen,21.95 +cmmlu-arts,dd77b8,accuracy,gen,22.50 +cmmlu-astronomy,1e49db,accuracy,gen,9.70 +cmmlu-business_ethics,dc78cb,accuracy,gen,25.36 +cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,13.12 +cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,18.32 +cmmlu-chinese_food_culture,2d568a,accuracy,gen,19.85 +cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,16.82 +cmmlu-chinese_history,4cc7ed,accuracy,gen,8.05 +cmmlu-chinese_literature,af3c41,accuracy,gen,2.45 +cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,16.20 +cmmlu-clinical_knowledge,c55b1d,accuracy,gen,11.81 +cmmlu-college_actuarial_science,d3c360,accuracy,gen,4.72 +cmmlu-college_education,df8790,accuracy,gen,25.23 +cmmlu-college_engineering_hydrology,673f23,accuracy,gen,22.64 +cmmlu-college_law,524c3a,accuracy,gen,17.59 +cmmlu-college_mathematics,e4ebad,accuracy,gen,7.62 +cmmlu-college_medical_statistics,55af35,accuracy,gen,14.15 +cmmlu-college_medicine,702f48,accuracy,gen,20.51 +cmmlu-computer_science,637007,accuracy,gen,20.59 +cmmlu-computer_security,932b6b,accuracy,gen,19.30 +cmmlu-conceptual_physics,cfc077,accuracy,gen,17.69 +cmmlu-construction_project_management,968a4a,accuracy,gen,20.14 +cmmlu-economics,ddaf7c,accuracy,gen,21.38 +cmmlu-education,c35963,accuracy,gen,13.50 +cmmlu-electrical_engineering,70e98a,accuracy,gen,20.35 +cmmlu-elementary_chinese,cbcd6a,accuracy,gen,24.21 +cmmlu-elementary_commonsense,a67f37,accuracy,gen,24.24 +cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,5.88 +cmmlu-elementary_mathematics,a9d403,accuracy,gen,25.65 +cmmlu-ethnology,31955f,accuracy,gen,17.04 +cmmlu-food_science,741d8e,accuracy,gen,23.08 +cmmlu-genetics,c326f7,accuracy,gen,10.80 +cmmlu-global_facts,0a1236,accuracy,gen,14.09 +cmmlu-high_school_biology,2be811,accuracy,gen,6.51 +cmmlu-high_school_chemistry,d63c05,accuracy,gen,19.70 +cmmlu-high_school_geography,5cd489,accuracy,gen,18.64 +cmmlu-high_school_mathematics,6b2087,accuracy,gen,21.34 +cmmlu-high_school_physics,3df353,accuracy,gen,10.00 +cmmlu-high_school_politics,7a88d8,accuracy,gen,9.09 +cmmlu-human_sexuality,54ac98,accuracy,gen,17.46 +cmmlu-international_law,0f5d40,accuracy,gen,12.43 +cmmlu-journalism,a4f6a0,accuracy,gen,23.84 +cmmlu-jurisprudence,7843da,accuracy,gen,22.38 +cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,21.03 +cmmlu-logical,15a71b,accuracy,gen,14.63 +cmmlu-machine_learning,bc6ad4,accuracy,gen,4.92 +cmmlu-management,e5e8db,accuracy,gen,19.05 +cmmlu-marketing,8b4c18,accuracy,gen,12.78 +cmmlu-marxist_theory,75eb79,accuracy,gen,23.28 +cmmlu-modern_chinese,83a9b7,accuracy,gen,23.28 +cmmlu-nutrition,adfff7,accuracy,gen,22.07 +cmmlu-philosophy,75e22d,accuracy,gen,20.95 +cmmlu-professional_accounting,0edc91,accuracy,gen,24.57 +cmmlu-professional_law,d24af5,accuracy,gen,17.06 +cmmlu-professional_medicine,134139,accuracy,gen,18.62 +cmmlu-professional_psychology,ec920e,accuracy,gen,18.97 +cmmlu-public_relations,70ee06,accuracy,gen,6.32 +cmmlu-security_study,45f96f,accuracy,gen,22.96 +cmmlu-sociology,485285,accuracy,gen,24.34 +cmmlu-sports_science,838cfe,accuracy,gen,18.79 +cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,19.46 +cmmlu-virology,8925bf,accuracy,gen,20.71 +cmmlu-world_history,57c97c,accuracy,gen,3.11 +cmmlu-world_religions,1d0f4b,accuracy,gen,20.62 +gsm8k,1d7fe4,accuracy,gen,2.58 +math,265cce,accuracy,gen,0.20 +lukaemon_mmlu_college_biology,8c2e29,accuracy,gen,1.39 +lukaemon_mmlu_college_chemistry,0afccd,accuracy,gen,6.00 +lukaemon_mmlu_college_computer_science,c1c1b4,accuracy,gen,3.00 +lukaemon_mmlu_college_mathematics,9deed0,accuracy,gen,3.00 +lukaemon_mmlu_college_physics,f5cf5e,accuracy,gen,1.96 +lukaemon_mmlu_electrical_engineering,3d694d,accuracy,gen,3.45 +lukaemon_mmlu_astronomy,7ef16f,accuracy,gen,0.66 +lukaemon_mmlu_anatomy,2d597d,accuracy,gen,2.22 +lukaemon_mmlu_abstract_algebra,ec092c,accuracy,gen,2.00 +lukaemon_mmlu_machine_learning,d489ae,accuracy,gen,3.57 +lukaemon_mmlu_clinical_knowledge,af10df,accuracy,gen,1.51 +lukaemon_mmlu_global_facts,cad9e0,accuracy,gen,3.00 +lukaemon_mmlu_management,65f310,accuracy,gen,11.65 +lukaemon_mmlu_nutrition,80bf96,accuracy,gen,1.63 +lukaemon_mmlu_marketing,9a98c0,accuracy,gen,2.56 +lukaemon_mmlu_professional_accounting,9cc7e2,accuracy,gen,1.06 +lukaemon_mmlu_high_school_geography,c28a4c,accuracy,gen,2.02 +lukaemon_mmlu_international_law,408d4e,accuracy,gen,0.83 +lukaemon_mmlu_moral_scenarios,9f30a6,accuracy,gen,0.00 +lukaemon_mmlu_computer_security,2753c1,accuracy,gen,0.00 +lukaemon_mmlu_high_school_microeconomics,af9eae,accuracy,gen,0.84 +lukaemon_mmlu_professional_law,7c7a62,accuracy,gen,7.30 +lukaemon_mmlu_medical_genetics,b1a3a7,accuracy,gen,0.00 +lukaemon_mmlu_professional_psychology,c6b790,accuracy,gen,1.31 +lukaemon_mmlu_jurisprudence,f41074,accuracy,gen,0.00 +lukaemon_mmlu_world_religions,d44a95,accuracy,gen,2.34 +lukaemon_mmlu_philosophy,d36ef3,accuracy,gen,4.50 +lukaemon_mmlu_virology,0a5f8e,accuracy,gen,1.20 +lukaemon_mmlu_high_school_chemistry,5b2ef9,accuracy,gen,10.84 +lukaemon_mmlu_public_relations,4c7898,accuracy,gen,3.64 +lukaemon_mmlu_high_school_macroeconomics,3f841b,accuracy,gen,0.00 +lukaemon_mmlu_human_sexuality,4d1f3e,accuracy,gen,2.29 +lukaemon_mmlu_elementary_mathematics,0f5d3a,accuracy,gen,4.76 +lukaemon_mmlu_high_school_physics,0dd929,accuracy,gen,1.32 +lukaemon_mmlu_high_school_computer_science,bf31fd,accuracy,gen,15.00 +lukaemon_mmlu_high_school_european_history,d1b67e,accuracy,gen,3.03 +lukaemon_mmlu_business_ethics,af53f3,accuracy,gen,1.00 +lukaemon_mmlu_moral_disputes,48239e,accuracy,gen,1.16 +lukaemon_mmlu_high_school_statistics,47e18e,accuracy,gen,2.78 +lukaemon_mmlu_miscellaneous,573569,accuracy,gen,18.01 +lukaemon_mmlu_formal_logic,7a0414,accuracy,gen,12.70 +lukaemon_mmlu_high_school_government_and_politics,d907eb,accuracy,gen,0.52 +lukaemon_mmlu_prehistory,65aa94,accuracy,gen,1.85 +lukaemon_mmlu_security_studies,9ea7d3,accuracy,gen,0.41 +lukaemon_mmlu_high_school_biology,775183,accuracy,gen,1.61 +lukaemon_mmlu_logical_fallacies,19746a,accuracy,gen,1.84 +lukaemon_mmlu_high_school_world_history,6665dc,accuracy,gen,2.53 +lukaemon_mmlu_professional_medicine,a05bab,accuracy,gen,0.37 +lukaemon_mmlu_high_school_mathematics,0e6a7e,accuracy,gen,0.74 +lukaemon_mmlu_college_medicine,5215f1,accuracy,gen,1.73 +lukaemon_mmlu_high_school_us_history,b5f235,accuracy,gen,4.41 +lukaemon_mmlu_sociology,4980ec,accuracy,gen,0.50 +lukaemon_mmlu_econometrics,4d590b,accuracy,gen,18.42 +lukaemon_mmlu_high_school_psychology,440e96,accuracy,gen,0.37 +lukaemon_mmlu_human_aging,d0a8e1,accuracy,gen,2.24 +lukaemon_mmlu_us_foreign_policy,adcc88,accuracy,gen,0.00 +lukaemon_mmlu_conceptual_physics,a111d3,accuracy,gen,2.13 +agieval-chinese,-,naive_average,gen,5.95 +agieval-english,-,naive_average,gen,2.44 +agieval-gaokao,-,naive_average,gen,5.66 +agieval,-,naive_average,gen,4.45 +mmlu-humanities,-,naive_average,gen,3.27 +mmlu-stem,-,naive_average,gen,3.50 +mmlu-social-science,-,naive_average,gen,2.53 +mmlu-other,-,naive_average,gen,3.54 +mmlu,-,naive_average,gen,3.25 +mmlu-weighted,-,weighted_average,gen,3.70 +cmmlu-humanities,-,naive_average,gen,15.32 +cmmlu-stem,-,naive_average,gen,15.38 +cmmlu-social-science,-,naive_average,gen,19.02 +cmmlu-other,-,naive_average,gen,18.56 +cmmlu-china-specific,-,naive_average,gen,16.95 +cmmlu,-,naive_average,gen,17.28 +ceval-stem,-,naive_average,gen,29.79 +ceval-social-science,-,naive_average,gen,29.03 +ceval-humanities,-,naive_average,gen,26.43 +ceval-other,-,naive_average,gen,31.58 +ceval-hard,-,naive_average,gen,28.82 +ceval,-,naive_average,gen,29.31 +GaokaoBench,-,weighted_average,gen,11.25 diff --git a/results/ISFP.csv b/results/ISFP.csv index 1f855f2..eb0a22e 100644 --- a/results/ISFP.csv +++ b/results/ISFP.csv @@ -1,242 +1,255 @@ -dataset,version,metric,mode,opencompass.models.huggingface.HuggingFace_FarReelAILab_Machine_Mindset_en_ISFP -GaokaoBench_2010-2022_Math_II_MCQs,5b0b29,score,gen,5.5 -GaokaoBench_2010-2022_Math_I_MCQs,5b0b29,score,gen,3.27 -GaokaoBench_2010-2022_History_MCQs,3613b5,score,gen,2.79 -GaokaoBench_2010-2022_Biology_MCQs,d26e80,score,gen,2.67 -GaokaoBench_2010-2022_Political_Science_MCQs,70fce9,score,gen,3.12 -GaokaoBench_2010-2022_Physics_MCQs,8a0c30,score,gen,6.25 -GaokaoBench_2010-2022_Chemistry_MCQs,852bbd,score,gen,0.81 -GaokaoBench_2010-2013_English_MCQs,01b50f,score,gen,19.05 -GaokaoBench_2010-2022_Chinese_Modern_Lit,e19c31,score,gen,0 -GaokaoBench_2010-2022_English_Fill_in_Blanks,924021,score,gen,14 -GaokaoBench_2012-2022_English_Cloze_Test,11f6ce,score,gen,0.77 -GaokaoBench_2010-2022_Geography_MCQs,862192,score,gen,4.21 -GaokaoBench_2010-2022_English_Reading_Comp,ffdef4,score,gen,1.7 -GaokaoBench_2010-2022_Chinese_Lang_and_Usage_MCQs,ba10b2,score,gen,8.75 -GaokaoBench_2010-2022_Math_I_Fill-in-the-Blank,9dd6c7,score,gen,0 -GaokaoBench_2010-2022_Math_II_Fill-in-the-Blank,9dd6c7,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Famous_Passages_and_Sentences_Dictation,58053d,score,gen,0 -GaokaoBench_2014-2022_English_Language_Cloze_Passage,d431f7,score,gen,0 -GaokaoBench_2010-2022_Geography_Open-ended_Questions,475d13,score,gen,0 -GaokaoBench_2010-2022_Chemistry_Open-ended_Questions,0bccc3,score,gen,0 -GaokaoBench_2010-2022_Math_I_Open-ended_Questions,8a0cf5,score,gen,0 -GaokaoBench_2010-2022_History_Open-ended_Questions,9fbad8,score,gen,0 -GaokaoBench_2010-2022_Biology_Open-ended_Questions,e0cb29,score,gen,0 -GaokaoBench_2010-2022_Math_II_Open-ended_Questions,8a0cf5,score,gen,0 -GaokaoBench_2010-2022_Physics_Open-ended_Questions,423d19,score,gen,0 -GaokaoBench_2010-2022_Political_Science_Open-ended_Questions,0eee0a,score,gen,0 -GaokaoBench_2012-2022_English_Language_Error_Correction,6a3cae,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Ancient_Poetry_Reading,ee6cc7,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Practical_Text_Reading,4dea5a,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Literary_Text_Reading,979d8b,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Classical_Chinese_Reading,9de717,score,gen,0 -GaokaoBench_2010-2022_Chinese_Language_Language_and_Writing_Skills_Open-ended_Questions,d2ed84,score,gen,0 -agieval-gaokao-chinese,774562,accuracy,gen,4.47 -agieval-gaokao-english,cb5bc6,accuracy,gen,5.88 -agieval-gaokao-geography,2ca56f,accuracy,gen,3.52 -agieval-gaokao-history,9c3ae0,accuracy,gen,7.66 -agieval-gaokao-biology,277c85,accuracy,gen,7.62 -agieval-gaokao-chemistry,d62fd4,accuracy,gen,6.28 -agieval-gaokao-mathqa,-,-,-,- -agieval-logiqa-zh,-,-,-,- -agieval-lsat-ar,ed1edf,accuracy,gen,2.61 -agieval-lsat-lr,-,-,-,- -agieval-lsat-rc,33077d,accuracy,gen,5.2 -agieval-logiqa-en,-,-,-,- -agieval-sat-math,6c970d,accuracy,gen,4.55 -agieval-sat-en,4e3fef,accuracy,gen,5.83 -agieval-sat-en-without-passage,4e3fef,accuracy,gen,3.4 -agieval-aqua-rat,c090ca,accuracy,gen,0.39 -agieval-gaokao-physics,7.70E+06,accuracy,gen,9.5 -agieval-jec-qa-kd,b1e586,accuracy,gen,4.9 -agieval-jec-qa-ca,-,-,-,- -agieval-gaokao-mathcloze,-,-,-,- -agieval-math,-,-,-,- -ceval-computer_network,db9ce2,accuracy,gen,26.32 -ceval-operating_system,1c2571,accuracy,gen,47.37 -ceval-computer_architecture,a74dad,accuracy,gen,23.81 -ceval-college_programming,4ca32a,accuracy,gen,32.43 -ceval-college_physics,963fa8,accuracy,gen,10.53 -ceval-college_chemistry,e78857,accuracy,gen,12.5 -ceval-advanced_mathematics,ce03e2,accuracy,gen,26.32 -ceval-probability_and_statistics,65e812,accuracy,gen,44.44 -ceval-discrete_mathematics,e894ae,accuracy,gen,37.5 -ceval-electrical_engineer,ae42b9,accuracy,gen,27.03 -ceval-metrology_engineer,ee34ea,accuracy,gen,37.5 -ceval-high_school_mathematics,1dc5bf,accuracy,gen,11.11 -ceval-high_school_physics,adf25f,accuracy,gen,47.37 -ceval-high_school_chemistry,2ed27f,accuracy,gen,31.58 -ceval-high_school_biology,8e2b9a,accuracy,gen,10.53 -ceval-middle_school_mathematics,bee8d5,accuracy,gen,15.79 -ceval-middle_school_biology,86817c,accuracy,gen,23.81 -ceval-middle_school_physics,8accf6,accuracy,gen,57.89 -ceval-middle_school_chemistry,167a15,accuracy,gen,40 -ceval-veterinary_medicine,b4e08d,accuracy,gen,30.43 -ceval-college_economics,f3f4e6,accuracy,gen,45.45 -ceval-business_administration,c1614e,accuracy,gen,33.33 -ceval-marxism,cf874c,accuracy,gen,26.32 -ceval-mao_zedong_thought,51c7a4,accuracy,gen,33.33 -ceval-education_science,591fee,accuracy,gen,34.48 -ceval-teacher_qualification,4e4ced,accuracy,gen,22.73 -ceval-high_school_politics,5c0de2,accuracy,gen,26.32 -ceval-high_school_geography,865461,accuracy,gen,31.58 -ceval-middle_school_politics,5be3e7,accuracy,gen,28.57 -ceval-middle_school_geography,8a63be,accuracy,gen,16.67 -ceval-modern_chinese_history,fc01af,accuracy,gen,21.74 -ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,26.32 -ceval-logic,f5b022,accuracy,gen,22.73 -ceval-law,a110a1,accuracy,gen,25 -ceval-chinese_language_and_literature,0f8b68,accuracy,gen,30.43 -ceval-art_studies,2a1300,accuracy,gen,15.15 -ceval-professional_tour_guide,4e673e,accuracy,gen,24.14 -ceval-legal_professional,ce8787,accuracy,gen,21.74 -ceval-high_school_chinese,315705,accuracy,gen,15.79 -ceval-high_school_history,7eb30a,accuracy,gen,40 -ceval-middle_school_history,48ab4a,accuracy,gen,22.73 -ceval-civil_servant,87d061,accuracy,gen,27.66 -ceval-sports_science,70f27b,accuracy,gen,15.79 -ceval-plant_protection,8941f9,accuracy,gen,36.36 -ceval-basic_medicine,c409d6,accuracy,gen,42.11 -ceval-clinical_medicine,49e82d,accuracy,gen,27.27 -ceval-urban_and_rural_planner,95b885,accuracy,gen,34.78 -ceval-accountant,2837,accuracy,gen,24.49 -ceval-fire_engineer,bc23f5,accuracy,gen,35.48 -ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,29.03 -ceval-tax_accountant,3a5e3c,accuracy,gen,24.49 -ceval-physician,6e277d,accuracy,gen,26.53 -cmmlu-agronomy,4c7f2c,accuracy,gen,14.79 -cmmlu-anatomy,ea09bf,accuracy,gen,18.92 -cmmlu-ancient_chinese,f7c97f,accuracy,gen,12.8 -cmmlu-arts,dd77b8,accuracy,gen,19.38 -cmmlu-astronomy,1e49db,accuracy,gen,8.48 -cmmlu-business_ethics,dc78cb,accuracy,gen,11 -cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,15 -cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,23.66 -cmmlu-chinese_food_culture,2d568a,accuracy,gen,5.15 -cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,12.15 -cmmlu-chinese_history,4cc7ed,accuracy,gen,10.84 -cmmlu-chinese_literature,af3c41,accuracy,gen,0.49 -cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,8.94 -cmmlu-clinical_knowledge,c55b1d,accuracy,gen,11.81 -cmmlu-college_actuarial_science,d3c360,accuracy,gen,0.94 -cmmlu-college_education,df8790,accuracy,gen,16.82 -cmmlu-college_engineering_hydrology,673f23,accuracy,gen,29.25 -cmmlu-college_law,524c3a,accuracy,gen,15.74 -cmmlu-college_mathematics,e4ebad,accuracy,gen,6.67 -cmmlu-college_medical_statistics,55af35,accuracy,gen,16.98 -cmmlu-college_medicine,702f48,accuracy,gen,21.25 -cmmlu-computer_science,637007,accuracy,gen,17.65 -cmmlu-computer_security,932b6b,accuracy,gen,15.79 -cmmlu-conceptual_physics,cfc077,accuracy,gen,7.48 -cmmlu-construction_project_management,968a4a,accuracy,gen,23.02 -cmmlu-economics,ddaf7c,accuracy,gen,15.72 -cmmlu-education,c35963,accuracy,gen,7.98 -cmmlu-electrical_engineering,70e98a,accuracy,gen,17.44 -cmmlu-elementary_chinese,cbcd6a,accuracy,gen,17.46 -cmmlu-elementary_commonsense,a67f37,accuracy,gen,19.19 -cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,18.49 -cmmlu-elementary_mathematics,a9d403,accuracy,gen,23.04 -cmmlu-ethnology,31955f,accuracy,gen,14.07 -cmmlu-food_science,741d8e,accuracy,gen,15.38 -cmmlu-genetics,c326f7,accuracy,gen,18.75 -cmmlu-global_facts,0a1236,accuracy,gen,17.45 -cmmlu-high_school_biology,2be811,accuracy,gen,18.34 -cmmlu-high_school_chemistry,d63c05,accuracy,gen,7.58 -cmmlu-high_school_geography,5cd489,accuracy,gen,10.17 -cmmlu-high_school_mathematics,6b2087,accuracy,gen,4.88 -cmmlu-high_school_physics,3df353,accuracy,gen,10.91 -cmmlu-high_school_politics,7a88d8,accuracy,gen,2.1 -cmmlu-human_sexuality,54ac98,accuracy,gen,14.29 -cmmlu-international_law,0f5d40,accuracy,gen,22.16 -cmmlu-journalism,a4f6a0,accuracy,gen,15.7 -cmmlu-jurisprudence,-,-,-,- -cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,28.04 -cmmlu-logical,15a71b,accuracy,gen,13.82 -cmmlu-machine_learning,bc6ad4,accuracy,gen,4.1 -cmmlu-management,e5e8db,accuracy,gen,10.95 -cmmlu-marketing,8b4c18,accuracy,gen,12.22 -cmmlu-marxist_theory,75eb79,accuracy,gen,23.81 -cmmlu-modern_chinese,83a9b7,accuracy,gen,17.24 -cmmlu-nutrition,adfff7,accuracy,gen,16.55 -cmmlu-philosophy,75e22d,accuracy,gen,14.29 -cmmlu-professional_accounting,0edc91,accuracy,gen,9.14 -cmmlu-professional_law,-,-,-,- -cmmlu-professional_medicine,-,-,-,- -cmmlu-professional_psychology,ec920e,accuracy,gen,16.81 -cmmlu-public_relations,70ee06,accuracy,gen,10.92 -cmmlu-security_study,45f96f,accuracy,gen,14.07 -cmmlu-sociology,485285,accuracy,gen,7.52 -cmmlu-sports_science,838cfe,accuracy,gen,17.58 -cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,12.43 -cmmlu-virology,8925bf,accuracy,gen,20.71 -cmmlu-world_history,57c97c,accuracy,gen,7.45 -cmmlu-world_religions,1d0f4b,accuracy,gen,14.37 -gsm8k,1d7fe4,accuracy,gen,2.27 -math,-,-,-,- -lukaemon_mmlu_college_biology,8c2e29,accuracy,gen,0 -lukaemon_mmlu_college_chemistry,0afccd,accuracy,gen,1 -lukaemon_mmlu_college_computer_science,c1c1b4,accuracy,gen,3 -lukaemon_mmlu_college_mathematics,9deed0,accuracy,gen,3 -lukaemon_mmlu_college_physics,f5cf5e,accuracy,gen,0.98 -lukaemon_mmlu_electrical_engineering,3d694d,accuracy,gen,0 -lukaemon_mmlu_astronomy,7ef16f,accuracy,gen,0 -lukaemon_mmlu_anatomy,2d597d,accuracy,gen,0 -lukaemon_mmlu_abstract_algebra,ec092c,accuracy,gen,0 -lukaemon_mmlu_machine_learning,d489ae,accuracy,gen,0 -lukaemon_mmlu_clinical_knowledge,af10df,accuracy,gen,0 -lukaemon_mmlu_global_facts,cad9e0,accuracy,gen,1 -lukaemon_mmlu_management,65f310,accuracy,gen,1.94 -lukaemon_mmlu_nutrition,80bf96,accuracy,gen,0.33 -lukaemon_mmlu_marketing,9a98c0,accuracy,gen,0 -lukaemon_mmlu_professional_accounting,9cc7e2,accuracy,gen,0.71 -lukaemon_mmlu_high_school_geography,c28a4c,accuracy,gen,0.51 -lukaemon_mmlu_international_law,408d4e,accuracy,gen,0 -lukaemon_mmlu_moral_scenarios,-,-,-,- -lukaemon_mmlu_computer_security,2753c1,accuracy,gen,0 -lukaemon_mmlu_high_school_microeconomics,af9eae,accuracy,gen,0 -lukaemon_mmlu_professional_law,7c7a62,accuracy,gen,7.17 -lukaemon_mmlu_medical_genetics,b1a3a7,accuracy,gen,0 -lukaemon_mmlu_professional_psychology,-,-,-,- -lukaemon_mmlu_jurisprudence,f41074,accuracy,gen,0 -lukaemon_mmlu_world_religions,d44a95,accuracy,gen,1.75 -lukaemon_mmlu_philosophy,d36ef3,accuracy,gen,0.64 -lukaemon_mmlu_virology,0a5f8e,accuracy,gen,0 -lukaemon_mmlu_high_school_chemistry,5b2ef9,accuracy,gen,1.97 -lukaemon_mmlu_public_relations,4c7898,accuracy,gen,0 -lukaemon_mmlu_high_school_macroeconomics,-,-,-,- -lukaemon_mmlu_human_sexuality,4d1f3e,accuracy,gen,1.53 -lukaemon_mmlu_elementary_mathematics,-,-,-,- -lukaemon_mmlu_high_school_physics,0dd929,accuracy,gen,0.66 -lukaemon_mmlu_high_school_computer_science,bf31fd,accuracy,gen,2 -lukaemon_mmlu_high_school_european_history,d1b67e,accuracy,gen,3.03 -lukaemon_mmlu_business_ethics,af53f3,accuracy,gen,3 -lukaemon_mmlu_moral_disputes,-,-,-,- -lukaemon_mmlu_high_school_statistics,47e18e,accuracy,gen,1.39 -lukaemon_mmlu_miscellaneous,-,-,-,- -lukaemon_mmlu_formal_logic,7a0414,accuracy,gen,4.76 -lukaemon_mmlu_high_school_government_and_politics,d907eb,accuracy,gen,0 -lukaemon_mmlu_prehistory,-,-,-,- -lukaemon_mmlu_security_studies,9ea7d3,accuracy,gen,1.22 -lukaemon_mmlu_high_school_biology,775183,accuracy,gen,0 -lukaemon_mmlu_logical_fallacies,19746a,accuracy,gen,0 -lukaemon_mmlu_high_school_world_history,6665dc,accuracy,gen,0.84 -lukaemon_mmlu_professional_medicine,a05bab,accuracy,gen,0 -lukaemon_mmlu_high_school_mathematics,0e6a7e,accuracy,gen,1.48 -lukaemon_mmlu_college_medicine,5215f1,accuracy,gen,0.58 -lukaemon_mmlu_high_school_us_history,b5f235,accuracy,gen,3.43 -lukaemon_mmlu_sociology,4980ec,accuracy,gen,0 -lukaemon_mmlu_econometrics,4d590b,accuracy,gen,2.63 -lukaemon_mmlu_high_school_psychology,-,-,-,- -lukaemon_mmlu_human_aging,d0a8e1,accuracy,gen,0 -lukaemon_mmlu_us_foreign_policy,adcc88,accuracy,gen,0 -lukaemon_mmlu_conceptual_physics,a111d3,accuracy,gen,0.43 -cmmlu-stem,-,naive_average,gen,13.65 -cmmlu-social-science,-,naive_average,gen,12 -cmmlu-china-specific,-,naive_average,gen,12.97 -ceval-stem,-,naive_average,gen,29.71 -ceval-social-science,-,naive_average,gen,29.88 -ceval-humanities,-,naive_average,gen,24.16 -ceval-other,-,naive_average,gen,29.45 -ceval-hard,-,naive_average,gen,27.67 -ceval,-,naive_average,gen,28.52 -GaokaoBench,-,weighted_average,gen,4.35 +dataset,version,metric,mode,opencompass.models.huggingface.HuggingFace_FarReelAILab_Machine_Mindset_en_ISFP +GaokaoBench_2010-2022_Math_II_MCQs,5b0b29,score,gen,5.50 +GaokaoBench_2010-2022_Math_I_MCQs,5b0b29,score,gen,3.27 +GaokaoBench_2010-2022_History_MCQs,3613b5,score,gen,2.79 +GaokaoBench_2010-2022_Biology_MCQs,d26e80,score,gen,2.67 +GaokaoBench_2010-2022_Political_Science_MCQs,70fce9,score,gen,3.12 +GaokaoBench_2010-2022_Physics_MCQs,8a0c30,score,gen,6.25 +GaokaoBench_2010-2022_Chemistry_MCQs,852bbd,score,gen,0.81 +GaokaoBench_2010-2013_English_MCQs,01b50f,score,gen,19.05 +GaokaoBench_2010-2022_Chinese_Modern_Lit,e19c31,score,gen,0.00 +GaokaoBench_2010-2022_English_Fill_in_Blanks,924021,score,gen,14.00 +GaokaoBench_2012-2022_English_Cloze_Test,11f6ce,score,gen,0.77 +GaokaoBench_2010-2022_Geography_MCQs,862192,score,gen,4.21 +GaokaoBench_2010-2022_English_Reading_Comp,ffdef4,score,gen,1.70 +GaokaoBench_2010-2022_Chinese_Lang_and_Usage_MCQs,ba10b2,score,gen,8.75 +GaokaoBench_2010-2022_Math_I_Fill-in-the-Blank,9dd6c7,score,gen,0.00 +GaokaoBench_2010-2022_Math_II_Fill-in-the-Blank,9dd6c7,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Famous_Passages_and_Sentences_Dictation,58053d,score,gen,0.00 +GaokaoBench_2014-2022_English_Language_Cloze_Passage,d431f7,score,gen,0.00 +GaokaoBench_2010-2022_Geography_Open-ended_Questions,475d13,score,gen,0.00 +GaokaoBench_2010-2022_Chemistry_Open-ended_Questions,0bccc3,score,gen,0.00 +GaokaoBench_2010-2022_Math_I_Open-ended_Questions,8a0cf5,score,gen,0.00 +GaokaoBench_2010-2022_History_Open-ended_Questions,9fbad8,score,gen,0.00 +GaokaoBench_2010-2022_Biology_Open-ended_Questions,e0cb29,score,gen,0.00 +GaokaoBench_2010-2022_Math_II_Open-ended_Questions,8a0cf5,score,gen,0.00 +GaokaoBench_2010-2022_Physics_Open-ended_Questions,423d19,score,gen,0.00 +GaokaoBench_2010-2022_Political_Science_Open-ended_Questions,0eee0a,score,gen,0.00 +GaokaoBench_2012-2022_English_Language_Error_Correction,6a3cae,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Ancient_Poetry_Reading,ee6cc7,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Practical_Text_Reading,4dea5a,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Literary_Text_Reading,979d8b,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Classical_Chinese_Reading,9de717,score,gen,0.00 +GaokaoBench_2010-2022_Chinese_Language_Language_and_Writing_Skills_Open-ended_Questions,d2ed84,score,gen,0.00 +agieval-gaokao-chinese,774562,accuracy,gen,4.47 +agieval-gaokao-english,cb5bc6,accuracy,gen,5.88 +agieval-gaokao-geography,2ca56f,accuracy,gen,3.52 +agieval-gaokao-history,9c3ae0,accuracy,gen,7.66 +agieval-gaokao-biology,277c85,accuracy,gen,7.62 +agieval-gaokao-chemistry,d62fd4,accuracy,gen,6.28 +agieval-gaokao-mathqa,e2ea74,accuracy,gen,4.56 +agieval-logiqa-zh,03474d,accuracy,gen,13.36 +agieval-lsat-ar,ed1edf,accuracy,gen,2.61 +agieval-lsat-lr,ec6882,accuracy,gen,3.92 +agieval-lsat-rc,33077d,accuracy,gen,5.20 +agieval-logiqa-en,c6ee60,accuracy,gen,3.23 +agieval-sat-math,6c970d,accuracy,gen,4.55 +agieval-sat-en,4e3fef,accuracy,gen,5.83 +agieval-sat-en-without-passage,4e3fef,accuracy,gen,3.40 +agieval-aqua-rat,c090ca,accuracy,gen,0.39 +agieval-gaokao-physics,7704e3,accuracy,gen,9.50 +agieval-jec-qa-kd,b1e586,accuracy,gen,4.90 +agieval-jec-qa-ca,47bc29,accuracy,gen,6.60 +agieval-gaokao-mathcloze,b2c3c3,score,gen,0.00 +agieval-math,e0c6d9,score,gen,0.40 +ceval-computer_network,db9ce2,accuracy,gen,26.32 +ceval-operating_system,1c2571,accuracy,gen,47.37 +ceval-computer_architecture,a74dad,accuracy,gen,23.81 +ceval-college_programming,4ca32a,accuracy,gen,32.43 +ceval-college_physics,963fa8,accuracy,gen,10.53 +ceval-college_chemistry,e78857,accuracy,gen,12.50 +ceval-advanced_mathematics,ce03e2,accuracy,gen,26.32 +ceval-probability_and_statistics,65e812,accuracy,gen,44.44 +ceval-discrete_mathematics,e894ae,accuracy,gen,37.50 +ceval-electrical_engineer,ae42b9,accuracy,gen,27.03 +ceval-metrology_engineer,ee34ea,accuracy,gen,37.50 +ceval-high_school_mathematics,1dc5bf,accuracy,gen,11.11 +ceval-high_school_physics,adf25f,accuracy,gen,47.37 +ceval-high_school_chemistry,2ed27f,accuracy,gen,31.58 +ceval-high_school_biology,8e2b9a,accuracy,gen,10.53 +ceval-middle_school_mathematics,bee8d5,accuracy,gen,15.79 +ceval-middle_school_biology,86817c,accuracy,gen,23.81 +ceval-middle_school_physics,8accf6,accuracy,gen,57.89 +ceval-middle_school_chemistry,167a15,accuracy,gen,40.00 +ceval-veterinary_medicine,b4e08d,accuracy,gen,30.43 +ceval-college_economics,f3f4e6,accuracy,gen,45.45 +ceval-business_administration,c1614e,accuracy,gen,33.33 +ceval-marxism,cf874c,accuracy,gen,26.32 +ceval-mao_zedong_thought,51c7a4,accuracy,gen,33.33 +ceval-education_science,591fee,accuracy,gen,34.48 +ceval-teacher_qualification,4e4ced,accuracy,gen,22.73 +ceval-high_school_politics,5c0de2,accuracy,gen,26.32 +ceval-high_school_geography,865461,accuracy,gen,31.58 +ceval-middle_school_politics,5be3e7,accuracy,gen,28.57 +ceval-middle_school_geography,8a63be,accuracy,gen,16.67 +ceval-modern_chinese_history,fc01af,accuracy,gen,21.74 +ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,26.32 +ceval-logic,f5b022,accuracy,gen,22.73 +ceval-law,a110a1,accuracy,gen,25.00 +ceval-chinese_language_and_literature,0f8b68,accuracy,gen,30.43 +ceval-art_studies,2a1300,accuracy,gen,15.15 +ceval-professional_tour_guide,4e673e,accuracy,gen,24.14 +ceval-legal_professional,ce8787,accuracy,gen,21.74 +ceval-high_school_chinese,315705,accuracy,gen,15.79 +ceval-high_school_history,7eb30a,accuracy,gen,40.00 +ceval-middle_school_history,48ab4a,accuracy,gen,22.73 +ceval-civil_servant,87d061,accuracy,gen,27.66 +ceval-sports_science,70f27b,accuracy,gen,15.79 +ceval-plant_protection,8941f9,accuracy,gen,36.36 +ceval-basic_medicine,c409d6,accuracy,gen,42.11 +ceval-clinical_medicine,49e82d,accuracy,gen,27.27 +ceval-urban_and_rural_planner,95b885,accuracy,gen,34.78 +ceval-accountant,002837,accuracy,gen,24.49 +ceval-fire_engineer,bc23f5,accuracy,gen,35.48 +ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,29.03 +ceval-tax_accountant,3a5e3c,accuracy,gen,24.49 +ceval-physician,6e277d,accuracy,gen,26.53 +cmmlu-agronomy,4c7f2c,accuracy,gen,14.79 +cmmlu-anatomy,ea09bf,accuracy,gen,18.92 +cmmlu-ancient_chinese,f7c97f,accuracy,gen,12.80 +cmmlu-arts,dd77b8,accuracy,gen,19.38 +cmmlu-astronomy,1e49db,accuracy,gen,8.48 +cmmlu-business_ethics,dc78cb,accuracy,gen,11.00 +cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,15.00 +cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,23.66 +cmmlu-chinese_food_culture,2d568a,accuracy,gen,5.15 +cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,12.15 +cmmlu-chinese_history,4cc7ed,accuracy,gen,10.84 +cmmlu-chinese_literature,af3c41,accuracy,gen,0.49 +cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,8.94 +cmmlu-clinical_knowledge,c55b1d,accuracy,gen,11.81 +cmmlu-college_actuarial_science,d3c360,accuracy,gen,0.94 +cmmlu-college_education,df8790,accuracy,gen,16.82 +cmmlu-college_engineering_hydrology,673f23,accuracy,gen,29.25 +cmmlu-college_law,524c3a,accuracy,gen,15.74 +cmmlu-college_mathematics,e4ebad,accuracy,gen,6.67 +cmmlu-college_medical_statistics,55af35,accuracy,gen,16.98 +cmmlu-college_medicine,702f48,accuracy,gen,21.25 +cmmlu-computer_science,637007,accuracy,gen,17.65 +cmmlu-computer_security,932b6b,accuracy,gen,15.79 +cmmlu-conceptual_physics,cfc077,accuracy,gen,7.48 +cmmlu-construction_project_management,968a4a,accuracy,gen,23.02 +cmmlu-economics,ddaf7c,accuracy,gen,15.72 +cmmlu-education,c35963,accuracy,gen,7.98 +cmmlu-electrical_engineering,70e98a,accuracy,gen,17.44 +cmmlu-elementary_chinese,cbcd6a,accuracy,gen,17.46 +cmmlu-elementary_commonsense,a67f37,accuracy,gen,19.19 +cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,18.49 +cmmlu-elementary_mathematics,a9d403,accuracy,gen,23.04 +cmmlu-ethnology,31955f,accuracy,gen,14.07 +cmmlu-food_science,741d8e,accuracy,gen,15.38 +cmmlu-genetics,c326f7,accuracy,gen,18.75 +cmmlu-global_facts,0a1236,accuracy,gen,17.45 +cmmlu-high_school_biology,2be811,accuracy,gen,18.34 +cmmlu-high_school_chemistry,d63c05,accuracy,gen,7.58 +cmmlu-high_school_geography,5cd489,accuracy,gen,10.17 +cmmlu-high_school_mathematics,6b2087,accuracy,gen,4.88 +cmmlu-high_school_physics,3df353,accuracy,gen,10.91 +cmmlu-high_school_politics,7a88d8,accuracy,gen,2.10 +cmmlu-human_sexuality,54ac98,accuracy,gen,14.29 +cmmlu-international_law,0f5d40,accuracy,gen,22.16 +cmmlu-journalism,a4f6a0,accuracy,gen,15.70 +cmmlu-jurisprudence,7843da,accuracy,gen,6.57 +cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,28.04 +cmmlu-logical,15a71b,accuracy,gen,13.82 +cmmlu-machine_learning,bc6ad4,accuracy,gen,4.10 +cmmlu-management,e5e8db,accuracy,gen,10.95 +cmmlu-marketing,8b4c18,accuracy,gen,12.22 +cmmlu-marxist_theory,75eb79,accuracy,gen,23.81 +cmmlu-modern_chinese,83a9b7,accuracy,gen,17.24 +cmmlu-nutrition,adfff7,accuracy,gen,16.55 +cmmlu-philosophy,75e22d,accuracy,gen,14.29 +cmmlu-professional_accounting,0edc91,accuracy,gen,9.14 +cmmlu-professional_law,d24af5,accuracy,gen,6.16 +cmmlu-professional_medicine,134139,accuracy,gen,19.15 +cmmlu-professional_psychology,ec920e,accuracy,gen,16.81 +cmmlu-public_relations,70ee06,accuracy,gen,10.92 +cmmlu-security_study,45f96f,accuracy,gen,14.07 +cmmlu-sociology,485285,accuracy,gen,7.52 +cmmlu-sports_science,838cfe,accuracy,gen,17.58 +cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,12.43 +cmmlu-virology,8925bf,accuracy,gen,20.71 +cmmlu-world_history,57c97c,accuracy,gen,7.45 +cmmlu-world_religions,1d0f4b,accuracy,gen,14.37 +gsm8k,1d7fe4,accuracy,gen,2.27 +math,265cce,accuracy,gen,0.18 +lukaemon_mmlu_college_biology,8c2e29,accuracy,gen,0.00 +lukaemon_mmlu_college_chemistry,0afccd,accuracy,gen,1.00 +lukaemon_mmlu_college_computer_science,c1c1b4,accuracy,gen,3.00 +lukaemon_mmlu_college_mathematics,9deed0,accuracy,gen,3.00 +lukaemon_mmlu_college_physics,f5cf5e,accuracy,gen,0.98 +lukaemon_mmlu_electrical_engineering,3d694d,accuracy,gen,0.00 +lukaemon_mmlu_astronomy,7ef16f,accuracy,gen,0.00 +lukaemon_mmlu_anatomy,2d597d,accuracy,gen,0.00 +lukaemon_mmlu_abstract_algebra,ec092c,accuracy,gen,0.00 +lukaemon_mmlu_machine_learning,d489ae,accuracy,gen,0.00 +lukaemon_mmlu_clinical_knowledge,af10df,accuracy,gen,0.00 +lukaemon_mmlu_global_facts,cad9e0,accuracy,gen,1.00 +lukaemon_mmlu_management,65f310,accuracy,gen,1.94 +lukaemon_mmlu_nutrition,80bf96,accuracy,gen,0.33 +lukaemon_mmlu_marketing,9a98c0,accuracy,gen,0.00 +lukaemon_mmlu_professional_accounting,9cc7e2,accuracy,gen,0.71 +lukaemon_mmlu_high_school_geography,c28a4c,accuracy,gen,0.51 +lukaemon_mmlu_international_law,408d4e,accuracy,gen,0.00 +lukaemon_mmlu_moral_scenarios,9f30a6,accuracy,gen,0.00 +lukaemon_mmlu_computer_security,2753c1,accuracy,gen,0.00 +lukaemon_mmlu_high_school_microeconomics,af9eae,accuracy,gen,0.00 +lukaemon_mmlu_professional_law,7c7a62,accuracy,gen,7.17 +lukaemon_mmlu_medical_genetics,b1a3a7,accuracy,gen,0.00 +lukaemon_mmlu_professional_psychology,c6b790,accuracy,gen,0.16 +lukaemon_mmlu_jurisprudence,f41074,accuracy,gen,0.00 +lukaemon_mmlu_world_religions,d44a95,accuracy,gen,1.75 +lukaemon_mmlu_philosophy,d36ef3,accuracy,gen,0.64 +lukaemon_mmlu_virology,0a5f8e,accuracy,gen,0.00 +lukaemon_mmlu_high_school_chemistry,5b2ef9,accuracy,gen,1.97 +lukaemon_mmlu_public_relations,4c7898,accuracy,gen,0.00 +lukaemon_mmlu_high_school_macroeconomics,3f841b,accuracy,gen,0.00 +lukaemon_mmlu_human_sexuality,4d1f3e,accuracy,gen,1.53 +lukaemon_mmlu_elementary_mathematics,0f5d3a,accuracy,gen,2.65 +lukaemon_mmlu_high_school_physics,0dd929,accuracy,gen,0.66 +lukaemon_mmlu_high_school_computer_science,bf31fd,accuracy,gen,2.00 +lukaemon_mmlu_high_school_european_history,d1b67e,accuracy,gen,3.03 +lukaemon_mmlu_business_ethics,af53f3,accuracy,gen,3.00 +lukaemon_mmlu_moral_disputes,48239e,accuracy,gen,0.00 +lukaemon_mmlu_high_school_statistics,47e18e,accuracy,gen,1.39 +lukaemon_mmlu_miscellaneous,573569,accuracy,gen,6.77 +lukaemon_mmlu_formal_logic,7a0414,accuracy,gen,4.76 +lukaemon_mmlu_high_school_government_and_politics,d907eb,accuracy,gen,0.00 +lukaemon_mmlu_prehistory,65aa94,accuracy,gen,0.00 +lukaemon_mmlu_security_studies,9ea7d3,accuracy,gen,1.22 +lukaemon_mmlu_high_school_biology,775183,accuracy,gen,0.00 +lukaemon_mmlu_logical_fallacies,19746a,accuracy,gen,0.00 +lukaemon_mmlu_high_school_world_history,6665dc,accuracy,gen,0.84 +lukaemon_mmlu_professional_medicine,a05bab,accuracy,gen,0.00 +lukaemon_mmlu_high_school_mathematics,0e6a7e,accuracy,gen,1.48 +lukaemon_mmlu_college_medicine,5215f1,accuracy,gen,0.58 +lukaemon_mmlu_high_school_us_history,b5f235,accuracy,gen,3.43 +lukaemon_mmlu_sociology,4980ec,accuracy,gen,0.00 +lukaemon_mmlu_econometrics,4d590b,accuracy,gen,2.63 +lukaemon_mmlu_high_school_psychology,440e96,accuracy,gen,0.18 +lukaemon_mmlu_human_aging,d0a8e1,accuracy,gen,0.00 +lukaemon_mmlu_us_foreign_policy,adcc88,accuracy,gen,0.00 +lukaemon_mmlu_conceptual_physics,a111d3,accuracy,gen,0.43 +agieval-chinese,-,naive_average,gen,6.20 +agieval-english,-,naive_average,gen,3.28 +agieval-gaokao,-,naive_average,gen,5.50 +agieval,-,naive_average,gen,4.95 +mmlu-humanities,-,naive_average,gen,1.66 +mmlu-stem,-,naive_average,gen,0.98 +mmlu-social-science,-,naive_average,gen,0.52 +mmlu-other,-,naive_average,gen,1.10 +mmlu,-,naive_average,gen,1.07 +mmlu-weighted,-,weighted_average,gen,1.72 +cmmlu-humanities,-,naive_average,gen,13.27 +cmmlu-stem,-,naive_average,gen,13.65 +cmmlu-social-science,-,naive_average,gen,12.00 +cmmlu-other,-,naive_average,gen,18.09 +cmmlu-china-specific,-,naive_average,gen,12.97 +cmmlu,-,naive_average,gen,14.03 +ceval-stem,-,naive_average,gen,29.71 +ceval-social-science,-,naive_average,gen,29.88 +ceval-humanities,-,naive_average,gen,24.16 +ceval-other,-,naive_average,gen,29.45 +ceval-hard,-,naive_average,gen,27.67 +ceval,-,naive_average,gen,28.52 +GaokaoBench,-,weighted_average,gen,4.35