| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4857|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.4612|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.2937|± |0.0407| | |
| | - high_school_european_history | 0|none | 0|acc |0.6364|± |0.0376| | |
| | - high_school_us_history | 0|none | 0|acc |0.6765|± |0.0328| | |
| | - high_school_world_history | 0|none | 0|acc |0.6540|± |0.0310| | |
| | - international_law | 0|none | 0|acc |0.6529|± |0.0435| | |
| | - jurisprudence | 0|none | 0|acc |0.5741|± |0.0478| | |
| | - logical_fallacies | 0|none | 0|acc |0.5031|± |0.0393| | |
| | - moral_disputes | 0|none | 0|acc |0.5029|± |0.0269| | |
| | - moral_scenarios | 0|none | 0|acc |0.2503|± |0.0145| | |
| | - philosophy | 0|none | 0|acc |0.6206|± |0.0276| | |
| | - prehistory | 0|none | 0|acc |0.5957|± |0.0273| | |
| | - professional_law | 0|none | 0|acc |0.3950|± |0.0125| | |
| | - world_religions | 0|none | 0|acc |0.7135|± |0.0347| | |
| | - other |N/A |none | 0|acc |0.5423|± |0.0087| | |
| | - business_ethics | 0|none | 0|acc |0.5100|± |0.0502| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4528|± |0.0306| | |
| | - college_medicine | 0|none | 0|acc |0.4509|± |0.0379| | |
| | - global_facts | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - human_aging | 0|none | 0|acc |0.5561|± |0.0333| | |
| | - management | 0|none | 0|acc |0.6408|± |0.0475| | |
| | - marketing | 0|none | 0|acc |0.7094|± |0.0297| | |
| | - medical_genetics | 0|none | 0|acc |0.5100|± |0.0502| | |
| | - miscellaneous | 0|none | 0|acc |0.6692|± |0.0168| | |
| | - nutrition | 0|none | 0|acc |0.5163|± |0.0286| | |
| | - professional_accounting | 0|none | 0|acc |0.3865|± |0.0290| | |
| | - professional_medicine | 0|none | 0|acc |0.4963|± |0.0304| | |
| | - virology | 0|none | 0|acc |0.4277|± |0.0385| | |
| | - social_sciences |N/A |none | 0|acc |0.5626|± |0.0088| | |
| | - econometrics | 0|none | 0|acc |0.2018|± |0.0378| | |
| | - high_school_geography | 0|none | 0|acc |0.5707|± |0.0353| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.6736|± |0.0338| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.4923|± |0.0253| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.5000|± |0.0325| | |
| | - high_school_psychology | 0|none | 0|acc |0.6312|± |0.0207| | |
| | - human_sexuality | 0|none | 0|acc |0.6183|± |0.0426| | |
| | - professional_psychology | 0|none | 0|acc |0.5049|± |0.0202| | |
| | - public_relations | 0|none | 0|acc |0.5636|± |0.0475| | |
| | - security_studies | 0|none | 0|acc |0.6041|± |0.0313| | |
| | - sociology | 0|none | 0|acc |0.6915|± |0.0327| | |
| | - us_foreign_policy | 0|none | 0|acc |0.7100|± |0.0456| | |
| | - stem |N/A |none | 0|acc |0.3914|± |0.0085| | |
| | - abstract_algebra | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - anatomy | 0|none | 0|acc |0.4741|± |0.0431| | |
| | - astronomy | 0|none | 0|acc |0.5263|± |0.0406| | |
| | - college_biology | 0|none | 0|acc |0.4653|± |0.0417| | |
| | - college_chemistry | 0|none | 0|acc |0.3800|± |0.0488| | |
| | - college_computer_science | 0|none | 0|acc |0.4300|± |0.0498| | |
| | - college_mathematics | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - college_physics | 0|none | 0|acc |0.2647|± |0.0439| | |
| | - computer_security | 0|none | 0|acc |0.6600|± |0.0476| | |
| | - conceptual_physics | 0|none | 0|acc |0.3319|± |0.0308| | |
| | - electrical_engineering | 0|none | 0|acc |0.4552|± |0.0415| | |
| | - elementary_mathematics | 0|none | 0|acc |0.3069|± |0.0238| | |
| | - high_school_biology | 0|none | 0|acc |0.5645|± |0.0282| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3842|± |0.0342| | |
| | - high_school_computer_science | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - high_school_mathematics | 0|none | 0|acc |0.3000|± |0.0279| | |
| | - high_school_physics | 0|none | 0|acc |0.2252|± |0.0341| | |
| | - high_school_statistics | 0|none | 0|acc |0.3796|± |0.0331| | |
| | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420| | |