| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4082|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.3783|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.3333|± |0.0422| | |
| | - high_school_european_history | 0|none | 0|acc |0.5818|± |0.0385| | |
| | - high_school_us_history | 0|none | 0|acc |0.4804|± |0.0351| | |
| | - high_school_world_history | 0|none | 0|acc |0.5781|± |0.0321| | |
| | - international_law | 0|none | 0|acc |0.5372|± |0.0455| | |
| | - jurisprudence | 0|none | 0|acc |0.4352|± |0.0479| | |
| | - logical_fallacies | 0|none | 0|acc |0.4785|± |0.0392| | |
| | - moral_disputes | 0|none | 0|acc |0.4017|± |0.0264| | |
| | - moral_scenarios | 0|none | 0|acc |0.2413|± |0.0143| | |
| | - philosophy | 0|none | 0|acc |0.4952|± |0.0284| | |
| | - prehistory | 0|none | 0|acc |0.4321|± |0.0276| | |
| | - professional_law | 0|none | 0|acc |0.3031|± |0.0117| | |
| | - world_religions | 0|none | 0|acc |0.6023|± |0.0375| | |
| | - other |N/A |none | 0|acc |0.4606|± |0.0089| | |
| | - business_ethics | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4717|± |0.0307| | |
| | - college_medicine | 0|none | 0|acc |0.4509|± |0.0379| | |
| | - global_facts | 0|none | 0|acc |0.3000|± |0.0461| | |
| | - human_aging | 0|none | 0|acc |0.3946|± |0.0328| | |
| | - management | 0|none | 0|acc |0.4369|± |0.0491| | |
| | - marketing | 0|none | 0|acc |0.5940|± |0.0322| | |
| | - medical_genetics | 0|none | 0|acc |0.5000|± |0.0503| | |
| | - miscellaneous | 0|none | 0|acc |0.5223|± |0.0179| | |
| | - nutrition | 0|none | 0|acc |0.4444|± |0.0285| | |
| | - professional_accounting | 0|none | 0|acc |0.3794|± |0.0289| | |
| | - professional_medicine | 0|none | 0|acc |0.4228|± |0.0300| | |
| | - virology | 0|none | 0|acc |0.3735|± |0.0377| | |
| | - social_sciences |N/A |none | 0|acc |0.4621|± |0.0089| | |
| | - econometrics | 0|none | 0|acc |0.2105|± |0.0384| | |
| | - high_school_geography | 0|none | 0|acc |0.4545|± |0.0355| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.5440|± |0.0359| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3872|± |0.0247| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3529|± |0.0310| | |
| | - high_school_psychology | 0|none | 0|acc |0.5468|± |0.0213| | |
| | - human_sexuality | 0|none | 0|acc |0.5115|± |0.0438| | |
| | - professional_psychology | 0|none | 0|acc |0.4297|± |0.0200| | |
| | - public_relations | 0|none | 0|acc |0.4273|± |0.0474| | |
| | - security_studies | 0|none | 0|acc |0.4571|± |0.0319| | |
| | - sociology | 0|none | 0|acc |0.5920|± |0.0348| | |
| | - us_foreign_policy | 0|none | 0|acc |0.6200|± |0.0488| | |
| | - stem |N/A |none | 0|acc |0.3486|± |0.0084| | |
| | - abstract_algebra | 0|none | 0|acc |0.2800|± |0.0451| | |
| | - anatomy | 0|none | 0|acc |0.4148|± |0.0426| | |
| | - astronomy | 0|none | 0|acc |0.4079|± |0.0400| | |
| | - college_biology | 0|none | 0|acc |0.4583|± |0.0417| | |
| | - college_chemistry | 0|none | 0|acc |0.3500|± |0.0479| | |
| | - college_computer_science | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - college_mathematics | 0|none | 0|acc |0.3100|± |0.0465| | |
| | - college_physics | 0|none | 0|acc |0.3137|± |0.0462| | |
| | - computer_security | 0|none | 0|acc |0.5200|± |0.0502| | |
| | - conceptual_physics | 0|none | 0|acc |0.3489|± |0.0312| | |
| | - electrical_engineering | 0|none | 0|acc |0.3655|± |0.0401| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2725|± |0.0229| | |
| | - high_school_biology | 0|none | 0|acc |0.4581|± |0.0283| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3399|± |0.0333| | |
| | - high_school_computer_science | 0|none | 0|acc |0.4100|± |0.0494| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2407|± |0.0261| | |
| | - high_school_physics | 0|none | 0|acc |0.2914|± |0.0371| | |
| | - high_school_statistics | 0|none | 0|acc |0.2870|± |0.0309| | |
| | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464| | |