| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4765|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.4499|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404| | |
| | - high_school_european_history | 0|none | 0|acc |0.6545|± |0.0371| | |
| | - high_school_us_history | 0|none | 0|acc |0.6520|± |0.0334| | |
| | - high_school_world_history | 0|none | 0|acc |0.6582|± |0.0309| | |
| | - international_law | 0|none | 0|acc |0.6198|± |0.0443| | |
| | - jurisprudence | 0|none | 0|acc |0.5278|± |0.0483| | |
| | - logical_fallacies | 0|none | 0|acc |0.4847|± |0.0393| | |
| | - moral_disputes | 0|none | 0|acc |0.5000|± |0.0269| | |
| | - moral_scenarios | 0|none | 0|acc |0.2380|± |0.0142| | |
| | - philosophy | 0|none | 0|acc |0.5916|± |0.0279| | |
| | - prehistory | 0|none | 0|acc |0.5741|± |0.0275| | |
| | - professional_law | 0|none | 0|acc |0.3931|± |0.0125| | |
| | - world_religions | 0|none | 0|acc |0.6667|± |0.0362| | |
| | - other |N/A |none | 0|acc |0.5291|± |0.0087| | |
| | - business_ethics | 0|none | 0|acc |0.5400|± |0.0501| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4340|± |0.0305| | |
| | - college_medicine | 0|none | 0|acc |0.4624|± |0.0380| | |
| | - global_facts | 0|none | 0|acc |0.2800|± |0.0451| | |
| | - human_aging | 0|none | 0|acc |0.5112|± |0.0335| | |
| | - management | 0|none | 0|acc |0.6505|± |0.0472| | |
| | - marketing | 0|none | 0|acc |0.6923|± |0.0302| | |
| | - medical_genetics | 0|none | 0|acc |0.5100|± |0.0502| | |
| | - miscellaneous | 0|none | 0|acc |0.6501|± |0.0171| | |
| | - nutrition | 0|none | 0|acc |0.5000|± |0.0286| | |
| | - professional_accounting | 0|none | 0|acc |0.3546|± |0.0285| | |
| | - professional_medicine | 0|none | 0|acc |0.5037|± |0.0304| | |
| | - virology | 0|none | 0|acc |0.4458|± |0.0387| | |
| | - social_sciences |N/A |none | 0|acc |0.5518|± |0.0088| | |
| | - econometrics | 0|none | 0|acc |0.2456|± |0.0405| | |
| | - high_school_geography | 0|none | 0|acc |0.5606|± |0.0354| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.6839|± |0.0336| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.4692|± |0.0253| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.5042|± |0.0325| | |
| | - high_school_psychology | 0|none | 0|acc |0.6073|± |0.0209| | |
| | - human_sexuality | 0|none | 0|acc |0.6107|± |0.0428| | |
| | - professional_psychology | 0|none | 0|acc |0.4951|± |0.0202| | |
| | - public_relations | 0|none | 0|acc |0.5364|± |0.0478| | |
| | - security_studies | 0|none | 0|acc |0.5959|± |0.0314| | |
| | - sociology | 0|none | 0|acc |0.6617|± |0.0335| | |
| | - us_foreign_policy | 0|none | 0|acc |0.7200|± |0.0451| | |
| | - stem |N/A |none | 0|acc |0.3907|± |0.0085| | |
| | - abstract_algebra | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - anatomy | 0|none | 0|acc |0.4889|± |0.0432| | |
| | - astronomy | 0|none | 0|acc |0.5132|± |0.0407| | |
| | - college_biology | 0|none | 0|acc |0.4792|± |0.0418| | |
| | - college_chemistry | 0|none | 0|acc |0.3700|± |0.0485| | |
| | - college_computer_science | 0|none | 0|acc |0.4200|± |0.0496| | |
| | - college_mathematics | 0|none | 0|acc |0.3500|± |0.0479| | |
| | - college_physics | 0|none | 0|acc |0.2941|± |0.0453| | |
| | - computer_security | 0|none | 0|acc |0.6200|± |0.0488| | |
| | - conceptual_physics | 0|none | 0|acc |0.3106|± |0.0303| | |
| | - electrical_engineering | 0|none | 0|acc |0.4621|± |0.0415| | |
| | - elementary_mathematics | 0|none | 0|acc |0.3148|± |0.0239| | |
| | - high_school_biology | 0|none | 0|acc |0.5581|± |0.0283| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3153|± |0.0327| | |
| | - high_school_computer_science | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2704|± |0.0271| | |
| | - high_school_physics | 0|none | 0|acc |0.2583|± |0.0357| | |
| | - high_school_statistics | 0|none | 0|acc |0.3981|± |0.0334| | |
| | - machine_learning | 0|none | 0|acc |0.3839|± |0.0462| | |