| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.3051|± |0.0039| | |
| | - humanities |N/A |none | 0|acc |0.2891|± |0.0066| | |
| | - formal_logic | 0|none | 0|acc |0.3095|± |0.0413| | |
| | - high_school_european_history | 0|none | 0|acc |0.2061|± |0.0316| | |
| | - high_school_us_history | 0|none | 0|acc |0.4118|± |0.0345| | |
| | - high_school_world_history | 0|none | 0|acc |0.3586|± |0.0312| | |
| | - international_law | 0|none | 0|acc |0.3471|± |0.0435| | |
| | - jurisprudence | 0|none | 0|acc |0.3611|± |0.0464| | |
| | - logical_fallacies | 0|none | 0|acc |0.2147|± |0.0323| | |
| | - moral_disputes | 0|none | 0|acc |0.3150|± |0.0250| | |
| | - moral_scenarios | 0|none | 0|acc |0.2324|± |0.0141| | |
| | - philosophy | 0|none | 0|acc |0.3376|± |0.0269| | |
| | - prehistory | 0|none | 0|acc |0.3302|± |0.0262| | |
| | - professional_law | 0|none | 0|acc |0.2679|± |0.0113| | |
| | - world_religions | 0|none | 0|acc |0.3626|± |0.0369| | |
| | - other |N/A |none | 0|acc |0.3251|± |0.0084| | |
| | - business_ethics | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - clinical_knowledge | 0|none | 0|acc |0.3170|± |0.0286| | |
| | - college_medicine | 0|none | 0|acc |0.3295|± |0.0358| | |
| | - global_facts | 0|none | 0|acc |0.2100|± |0.0409| | |
| | - human_aging | 0|none | 0|acc |0.2735|± |0.0299| | |
| | - management | 0|none | 0|acc |0.4078|± |0.0487| | |
| | - marketing | 0|none | 0|acc |0.3547|± |0.0313| | |
| | - medical_genetics | 0|none | 0|acc |0.3400|± |0.0476| | |
| | - miscellaneous | 0|none | 0|acc |0.3257|± |0.0168| | |
| | - nutrition | 0|none | 0|acc |0.3268|± |0.0269| | |
| | - professional_accounting | 0|none | 0|acc |0.2660|± |0.0264| | |
| | - professional_medicine | 0|none | 0|acc |0.3603|± |0.0292| | |
| | - virology | 0|none | 0|acc |0.4096|± |0.0383| | |
| | - social_sciences |N/A |none | 0|acc |0.3315|± |0.0084| | |
| | - econometrics | 0|none | 0|acc |0.2368|± |0.0400| | |
| | - high_school_geography | 0|none | 0|acc |0.3232|± |0.0333| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.3472|± |0.0344| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3231|± |0.0237| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.2647|± |0.0287| | |
| | - high_school_psychology | 0|none | 0|acc |0.3541|± |0.0205| | |
| | - human_sexuality | 0|none | 0|acc |0.3969|± |0.0429| | |
| | - professional_psychology | 0|none | 0|acc |0.2810|± |0.0182| | |
| | - public_relations | 0|none | 0|acc |0.3182|± |0.0446| | |
| | - security_studies | 0|none | 0|acc |0.3551|± |0.0306| | |
| | - sociology | 0|none | 0|acc |0.4328|± |0.0350| | |
| | - us_foreign_policy | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - stem |N/A |none | 0|acc |0.2835|± |0.0080| | |
| | - abstract_algebra | 0|none | 0|acc |0.2100|± |0.0409| | |
| | - anatomy | 0|none | 0|acc |0.3333|± |0.0407| | |
| | - astronomy | 0|none | 0|acc |0.3289|± |0.0382| | |
| | - college_biology | 0|none | 0|acc |0.3403|± |0.0396| | |
| | - college_chemistry | 0|none | 0|acc |0.3600|± |0.0482| | |
| | - college_computer_science | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - college_mathematics | 0|none | 0|acc |0.2600|± |0.0441| | |
| | - college_physics | 0|none | 0|acc |0.2647|± |0.0439| | |
| | - computer_security | 0|none | 0|acc |0.3000|± |0.0461| | |
| | - conceptual_physics | 0|none | 0|acc |0.3234|± |0.0306| | |
| | - electrical_engineering | 0|none | 0|acc |0.2897|± |0.0378| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2698|± |0.0229| | |
| | - high_school_biology | 0|none | 0|acc |0.3032|± |0.0261| | |
| | - high_school_chemistry | 0|none | 0|acc |0.1823|± |0.0272| | |
| | - high_school_computer_science | 0|none | 0|acc |0.2300|± |0.0423| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2519|± |0.0265| | |
| | - high_school_physics | 0|none | 0|acc |0.2450|± |0.0351| | |
| | - high_school_statistics | 0|none | 0|acc |0.3333|± |0.0321| | |
| | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420| | |