XinYuan-Qwen2-1_5B_summary.csv

dataset,version,metric,mode,XinYuan-Qwen2-1_5B-0822
lukaemon_mmlu_college_biology,caec7d,accuracy,gen,53.47
lukaemon_mmlu_college_chemistry,520aa6,accuracy,gen,40.00
lukaemon_mmlu_college_computer_science,99c216,accuracy,gen,45.00
lukaemon_mmlu_college_mathematics,678751,accuracy,gen,34.00
lukaemon_mmlu_college_physics,4f382c,accuracy,gen,29.41
lukaemon_mmlu_electrical_engineering,770ce3,accuracy,gen,55.17
lukaemon_mmlu_astronomy,d3ee01,accuracy,gen,50.66
lukaemon_mmlu_anatomy,72183b,accuracy,gen,54.07
lukaemon_mmlu_abstract_algebra,2db373,accuracy,gen,38.00
lukaemon_mmlu_machine_learning,0283bb,accuracy,gen,39.29
lukaemon_mmlu_clinical_knowledge,cb3218,accuracy,gen,57.74
lukaemon_mmlu_global_facts,ab07b6,accuracy,gen,33.00
lukaemon_mmlu_management,80876d,accuracy,gen,80.58
lukaemon_mmlu_nutrition,4543bd,accuracy,gen,65.03
lukaemon_mmlu_marketing,7394e3,accuracy,gen,82.05
lukaemon_mmlu_professional_accounting,444b7f,accuracy,gen,43.97
lukaemon_mmlu_high_school_geography,0780e6,accuracy,gen,69.19
lukaemon_mmlu_international_law,cf3179,accuracy,gen,72.73
lukaemon_mmlu_moral_scenarios,f6dbe2,accuracy,gen,26.37
lukaemon_mmlu_computer_security,ce7550,accuracy,gen,67.00
lukaemon_mmlu_high_school_microeconomics,04d21a,accuracy,gen,56.30
lukaemon_mmlu_professional_law,5f7e6c,accuracy,gen,42.37
lukaemon_mmlu_medical_genetics,881ef5,accuracy,gen,63.00
lukaemon_mmlu_professional_psychology,221a16,accuracy,gen,53.43
lukaemon_mmlu_jurisprudence,001f24,accuracy,gen,69.44
lukaemon_mmlu_world_religions,232c09,accuracy,gen,69.01
lukaemon_mmlu_philosophy,08042b,accuracy,gen,60.45
lukaemon_mmlu_virology,12e270,accuracy,gen,43.98
lukaemon_mmlu_high_school_chemistry,ae8820,accuracy,gen,49.75
lukaemon_mmlu_public_relations,e7d39b,accuracy,gen,58.18
lukaemon_mmlu_high_school_macroeconomics,a01685,accuracy,gen,56.15
lukaemon_mmlu_human_sexuality,42407c,accuracy,gen,67.18
lukaemon_mmlu_elementary_mathematics,269926,accuracy,gen,38.10
lukaemon_mmlu_high_school_physics,93278f,accuracy,gen,33.77
lukaemon_mmlu_high_school_computer_science,9965a5,accuracy,gen,56.00
lukaemon_mmlu_high_school_european_history,eefc90,accuracy,gen,65.45
lukaemon_mmlu_business_ethics,1dec08,accuracy,gen,66.00
lukaemon_mmlu_moral_disputes,a2173e,accuracy,gen,58.09
lukaemon_mmlu_high_school_statistics,8f3f3a,accuracy,gen,42.59
lukaemon_mmlu_miscellaneous,935647,accuracy,gen,70.50
lukaemon_mmlu_formal_logic,cfcb0c,accuracy,gen,37.30
lukaemon_mmlu_high_school_government_and_politics,3c52f9,accuracy,gen,75.65
lukaemon_mmlu_prehistory,bbb197,accuracy,gen,57.72
lukaemon_mmlu_security_studies,9b1743,accuracy,gen,70.61
lukaemon_mmlu_high_school_biology,37b125,accuracy,gen,63.55
lukaemon_mmlu_logical_fallacies,9cebb0,accuracy,gen,68.10
lukaemon_mmlu_high_school_world_history,048e7e,accuracy,gen,71.31
lukaemon_mmlu_professional_medicine,857144,accuracy,gen,49.26
lukaemon_mmlu_high_school_mathematics,ed4dc0,accuracy,gen,33.33
lukaemon_mmlu_college_medicine,38709e,accuracy,gen,49.71
lukaemon_mmlu_high_school_us_history,8932df,accuracy,gen,69.12
lukaemon_mmlu_sociology,c266a2,accuracy,gen,71.14
lukaemon_mmlu_econometrics,d1134d,accuracy,gen,35.09
lukaemon_mmlu_high_school_psychology,7db114,accuracy,gen,73.39
lukaemon_mmlu_human_aging,82a410,accuracy,gen,60.09
lukaemon_mmlu_us_foreign_policy,528cfe,accuracy,gen,78.00
lukaemon_mmlu_conceptual_physics,63588e,accuracy,gen,45.11
mmlu_pro_math,736233,accuracy,gen,17.25
mmlu_pro_physics,736233,accuracy,gen,13.16
mmlu_pro_chemistry,736233,accuracy,gen,9.54
mmlu_pro_law,736233,accuracy,gen,17.44
mmlu_pro_engineering,736233,accuracy,gen,11.35
mmlu_pro_other,736233,accuracy,gen,25.11
mmlu_pro_economics,736233,accuracy,gen,29.50
mmlu_pro_health,736233,accuracy,gen,21.64
mmlu_pro_psychology,736233,accuracy,gen,30.83
mmlu_pro_business,736233,accuracy,gen,17.11
mmlu_pro_biology,736233,accuracy,gen,31.52
mmlu_pro_philosophy,736233,accuracy,gen,20.84
mmlu_pro_computer_science,736233,accuracy,gen,23.90
mmlu_pro_history,736233,accuracy,gen,22.31
gsm8k,1d7fe4,accuracy,gen,57.62
ceval-computer_network,db9ce2,accuracy,gen,52.63
ceval-operating_system,1c2571,accuracy,gen,52.63
ceval-computer_architecture,a74dad,accuracy,gen,61.90
ceval-college_programming,4ca32a,accuracy,gen,67.57
ceval-college_physics,963fa8,accuracy,gen,36.84
ceval-college_chemistry,e78857,accuracy,gen,50.00
ceval-advanced_mathematics,ce03e2,accuracy,gen,57.89
ceval-probability_and_statistics,65e812,accuracy,gen,27.78
ceval-discrete_mathematics,e894ae,accuracy,gen,31.25
ceval-electrical_engineer,ae42b9,accuracy,gen,48.65
ceval-metrology_engineer,ee34ea,accuracy,gen,83.33
ceval-high_school_mathematics,1dc5bf,accuracy,gen,16.67
ceval-high_school_physics,adf25f,accuracy,gen,63.16
ceval-high_school_chemistry,2ed27f,accuracy,gen,68.42
ceval-high_school_biology,8e2b9a,accuracy,gen,84.21
ceval-middle_school_mathematics,bee8d5,accuracy,gen,63.16
ceval-middle_school_biology,86817c,accuracy,gen,85.71
ceval-middle_school_physics,8accf6,accuracy,gen,78.95
ceval-middle_school_chemistry,167a15,accuracy,gen,85.00
ceval-veterinary_medicine,b4e08d,accuracy,gen,78.26
ceval-college_economics,f3f4e6,accuracy,gen,72.73
ceval-business_administration,c1614e,accuracy,gen,72.73
ceval-marxism,cf874c,accuracy,gen,89.47
ceval-mao_zedong_thought,51c7a4,accuracy,gen,87.50
ceval-education_science,591fee,accuracy,gen,82.76
ceval-teacher_qualification,4e4ced,accuracy,gen,86.36
ceval-high_school_politics,5c0de2,accuracy,gen,78.95
ceval-high_school_geography,865461,accuracy,gen,73.68
ceval-middle_school_politics,5be3e7,accuracy,gen,85.71
ceval-middle_school_geography,8a63be,accuracy,gen,91.67
ceval-modern_chinese_history,fc01af,accuracy,gen,86.96
ceval-ideological_and_moral_cultivation,a2aa4a,accuracy,gen,100.00
ceval-logic,f5b022,accuracy,gen,63.64
ceval-law,a110a1,accuracy,gen,70.83
ceval-chinese_language_and_literature,0f8b68,accuracy,gen,52.17
ceval-art_studies,2a1300,accuracy,gen,69.70
ceval-professional_tour_guide,4e673e,accuracy,gen,82.76
ceval-legal_professional,ce8787,accuracy,gen,60.87
ceval-high_school_chinese,315705,accuracy,gen,68.42
ceval-high_school_history,7eb30a,accuracy,gen,80.00
ceval-middle_school_history,48ab4a,accuracy,gen,95.45
ceval-civil_servant,87d061,accuracy,gen,59.57
ceval-sports_science,70f27b,accuracy,gen,73.68
ceval-plant_protection,8941f9,accuracy,gen,63.64
ceval-basic_medicine,c409d6,accuracy,gen,84.21
ceval-clinical_medicine,49e82d,accuracy,gen,72.73
ceval-urban_and_rural_planner,95b885,accuracy,gen,67.39
ceval-accountant,002837,accuracy,gen,67.35
ceval-fire_engineer,bc23f5,accuracy,gen,61.29
ceval-environmental_impact_assessment_engineer,c64e2d,accuracy,gen,67.74
ceval-tax_accountant,3a5e3c,accuracy,gen,71.43
ceval-physician,6e277d,accuracy,gen,75.51
cmmlu-agronomy,4c7f2c,accuracy,gen,62.13
cmmlu-anatomy,ea09bf,accuracy,gen,75.00
cmmlu-ancient_chinese,f7c97f,accuracy,gen,32.93
cmmlu-arts,dd77b8,accuracy,gen,86.25
cmmlu-astronomy,1e49db,accuracy,gen,34.55
cmmlu-business_ethics,dc78cb,accuracy,gen,62.68
cmmlu-chinese_civil_service_exam,1de82c,accuracy,gen,66.25
cmmlu-chinese_driving_rule,b8a42b,accuracy,gen,96.18
cmmlu-chinese_food_culture,2d568a,accuracy,gen,59.56
cmmlu-chinese_foreign_policy,dc2427,accuracy,gen,68.22
cmmlu-chinese_history,4cc7ed,accuracy,gen,82.97
cmmlu-chinese_literature,af3c41,accuracy,gen,54.90
cmmlu-chinese_teacher_qualification,87de11,accuracy,gen,86.03
cmmlu-clinical_knowledge,c55b1d,accuracy,gen,62.03
cmmlu-college_actuarial_science,d3c360,accuracy,gen,37.74
cmmlu-college_education,df8790,accuracy,gen,80.37
cmmlu-college_engineering_hydrology,673f23,accuracy,gen,65.09
cmmlu-college_law,524c3a,accuracy,gen,62.04
cmmlu-college_mathematics,e4ebad,accuracy,gen,25.71
cmmlu-college_medical_statistics,55af35,accuracy,gen,58.49
cmmlu-college_medicine,702f48,accuracy,gen,70.70
cmmlu-computer_science,637007,accuracy,gen,69.12
cmmlu-computer_security,932b6b,accuracy,gen,87.72
cmmlu-conceptual_physics,cfc077,accuracy,gen,78.23
cmmlu-construction_project_management,968a4a,accuracy,gen,55.40
cmmlu-economics,ddaf7c,accuracy,gen,74.21
cmmlu-education,c35963,accuracy,gen,74.85
cmmlu-electrical_engineering,70e98a,accuracy,gen,77.91
cmmlu-elementary_chinese,cbcd6a,accuracy,gen,69.05
cmmlu-elementary_commonsense,a67f37,accuracy,gen,74.75
cmmlu-elementary_information_and_technology,d34d2a,accuracy,gen,86.97
cmmlu-elementary_mathematics,a9d403,accuracy,gen,43.91
cmmlu-ethnology,31955f,accuracy,gen,65.19
cmmlu-food_science,741d8e,accuracy,gen,64.34
cmmlu-genetics,c326f7,accuracy,gen,51.14
cmmlu-global_facts,0a1236,accuracy,gen,63.09
cmmlu-high_school_biology,2be811,accuracy,gen,75.15
cmmlu-high_school_chemistry,d63c05,accuracy,gen,54.55
cmmlu-high_school_geography,5cd489,accuracy,gen,74.58
cmmlu-high_school_mathematics,6b2087,accuracy,gen,37.80
cmmlu-high_school_physics,3df353,accuracy,gen,52.73
cmmlu-high_school_politics,7a88d8,accuracy,gen,67.83
cmmlu-human_sexuality,54ac98,accuracy,gen,63.49
cmmlu-international_law,0f5d40,accuracy,gen,54.59
cmmlu-journalism,a4f6a0,accuracy,gen,65.70
cmmlu-jurisprudence,7843da,accuracy,gen,76.40
cmmlu-legal_and_moral_basis,f906b0,accuracy,gen,96.26
cmmlu-logical,15a71b,accuracy,gen,62.60
cmmlu-machine_learning,bc6ad4,accuracy,gen,61.48
cmmlu-management,e5e8db,accuracy,gen,78.57
cmmlu-marketing,8b4c18,accuracy,gen,78.89
cmmlu-marxist_theory,75eb79,accuracy,gen,95.24
cmmlu-modern_chinese,83a9b7,accuracy,gen,47.41
cmmlu-nutrition,adfff7,accuracy,gen,71.03
cmmlu-philosophy,75e22d,accuracy,gen,74.29
cmmlu-professional_accounting,0edc91,accuracy,gen,84.57
cmmlu-professional_law,d24af5,accuracy,gen,63.51
cmmlu-professional_medicine,134139,accuracy,gen,63.30
cmmlu-professional_psychology,ec920e,accuracy,gen,79.31
cmmlu-public_relations,70ee06,accuracy,gen,67.82
cmmlu-security_study,45f96f,accuracy,gen,82.96
cmmlu-sociology,485285,accuracy,gen,66.81
cmmlu-sports_science,838cfe,accuracy,gen,64.85
cmmlu-traditional_chinese_medicine,3bbf64,accuracy,gen,76.76
cmmlu-virology,8925bf,accuracy,gen,72.19
cmmlu-world_history,57c97c,accuracy,gen,76.40
cmmlu-world_religions,1d0f4b,accuracy,gen,65.00
math,265cce,accuracy,gen,22.70
mbpp,830460,score,gen,33.80
mbpp,830460,pass,gen,169.00
mbpp,830460,timeout,gen,0.00
mbpp,830460,failed,gen,70.00
mbpp,830460,wrong_answer,gen,261.00
GPQA_extended,4baadb,accuracy,gen,29.30
GPQA_main,4baadb,accuracy,gen,28.35
GPQA_diamond,4baadb,accuracy,gen,26.26
bbh-temporal_sequences,e43931,score,gen,16.40
bbh-disambiguation_qa,d52c61,score,gen,43.20
bbh-date_understanding,a8000b,score,gen,46.80
bbh-tracking_shuffled_objects_three_objects,7964c0,score,gen,32.40
bbh-penguins_in_a_table,fceb27,score,gen,36.99
bbh-geometric_shapes,503c8f,score,gen,32.00
bbh-snarks,42d6ca,score,gen,55.06
bbh-ruin_names,408de8,score,gen,26.80
bbh-tracking_shuffled_objects_seven_objects,7964c0,score,gen,11.20
bbh-tracking_shuffled_objects_five_objects,7964c0,score,gen,16.40
bbh-logical_deduction_three_objects,45ebc5,score,gen,43.60
bbh-hyperbaton,5e5016,score,gen,64.80
bbh-logical_deduction_five_objects,45ebc5,score,gen,26.00
bbh-logical_deduction_seven_objects,45ebc5,score,gen,22.80
bbh-movie_recommendation,cc2fde,score,gen,47.60
bbh-salient_translation_error_detection,5b5f35,score,gen,30.00
bbh-reasoning_about_colored_objects,1cb761,score,gen,39.60
bbh-multistep_arithmetic_two,30f91e,score,gen,19.60
bbh-navigate,1576d9,score,gen,64.80
bbh-dyck_languages,805bea,score,gen,0.80
bbh-word_sorting,9a3f78,score,gen,3.60
bbh-sports_understanding,d3fa77,score,gen,57.20
bbh-boolean_expressions,612c92,score,gen,73.20
bbh-object_counting,781e5c,score,gen,56.40
bbh-formal_fallacies,eada96,score,gen,51.60
bbh-causal_judgement,89eaa4,score,gen,51.87
bbh-web_of_lies,0c0441,score,gen,65.20
IFEval,3321a3,Prompt-level-strict-accuracy,gen,24.03
IFEval,3321a3,Inst-level-strict-accuracy,gen,37.05
IFEval,3321a3,Prompt-level-loose-accuracy,gen,25.14
IFEval,3321a3,Inst-level-loose-accuracy,gen,38.49
ARC-c,1e0de5,accuracy,gen,71.19
hellaswag,6faab5,accuracy,gen,48.75
openai_humaneval,8e312c,humaneval_pass@1,gen,41.46
mmlu-humanities,-,naive_average,gen,59.04
mmlu-stem,-,naive_average,gen,45.70
mmlu-social-science,-,naive_average,gen,63.69
mmlu-other,-,naive_average,gen,58.84
mmlu,-,naive_average,gen,55.53
mmlu-weighted,-,weighted_average,gen,54.14
cmmlu-humanities,-,naive_average,gen,70.56
cmmlu-stem,-,naive_average,gen,57.10
cmmlu-social-science,-,naive_average,gen,69.72
cmmlu-other,-,naive_average,gen,73.06
cmmlu-china-specific,-,naive_average,gen,66.90
cmmlu,-,naive_average,gen,67.43
ceval-stem,-,naive_average,gen,59.70
ceval-social-science,-,naive_average,gen,82.16
ceval-humanities,-,naive_average,gen,75.53
ceval-other,-,naive_average,gen,69.50
ceval-hard,-,naive_average,gen,44.00
ceval,-,naive_average,gen,69.44
bbh,-,naive_average,gen,38.37