| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.5940|± |0.0039| | |
| | - humanities |N/A |none | 0|acc |0.5269|± |0.0067| | |
| | - formal_logic | 0|none | 0|acc |0.4365|± |0.0444| | |
| | - high_school_european_history | 0|none | 0|acc |0.6727|± |0.0366| | |
| | - high_school_us_history | 0|none | 0|acc |0.7598|± |0.0300| | |
| | - high_school_world_history | 0|none | 0|acc |0.7890|± |0.0266| | |
| | - international_law | 0|none | 0|acc |0.7769|± |0.0380| | |
| | - jurisprudence | 0|none | 0|acc |0.7222|± |0.0433| | |
| | - logical_fallacies | 0|none | 0|acc |0.6748|± |0.0368| | |
| | - moral_disputes | 0|none | 0|acc |0.6647|± |0.0254| | |
| | - moral_scenarios | 0|none | 0|acc |0.2380|± |0.0142| | |
| | - philosophy | 0|none | 0|acc |0.6720|± |0.0267| | |
| | - prehistory | 0|none | 0|acc |0.7037|± |0.0254| | |
| | - professional_law | 0|none | 0|acc |0.4374|± |0.0127| | |
| | - world_religions | 0|none | 0|acc |0.8070|± |0.0303| | |
| | - other |N/A |none | 0|acc |0.6746|± |0.0081| | |
| | - business_ethics | 0|none | 0|acc |0.5600|± |0.0499| | |
| | - clinical_knowledge | 0|none | 0|acc |0.7057|± |0.0280| | |
| | - college_medicine | 0|none | 0|acc |0.5954|± |0.0374| | |
| | - global_facts | 0|none | 0|acc |0.3500|± |0.0479| | |
| | - human_aging | 0|none | 0|acc |0.6816|± |0.0313| | |
| | - management | 0|none | 0|acc |0.8252|± |0.0376| | |
| | - marketing | 0|none | 0|acc |0.8419|± |0.0239| | |
| | - medical_genetics | 0|none | 0|acc |0.7500|± |0.0435| | |
| | - miscellaneous | 0|none | 0|acc |0.7739|± |0.0150| | |
| | - nutrition | 0|none | 0|acc |0.7026|± |0.0262| | |
| | - professional_accounting | 0|none | 0|acc |0.4362|± |0.0296| | |
| | - professional_medicine | 0|none | 0|acc |0.6581|± |0.0288| | |
| | - virology | 0|none | 0|acc |0.5000|± |0.0389| | |
| | - social_sciences |N/A |none | 0|acc |0.7004|± |0.0081| | |
| | - econometrics | 0|none | 0|acc |0.3421|± |0.0446| | |
| | - high_school_geography | 0|none | 0|acc |0.7475|± |0.0310| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.8187|± |0.0278| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.6051|± |0.0248| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.6555|± |0.0309| | |
| | - high_school_psychology | 0|none | 0|acc |0.7908|± |0.0174| | |
| | - human_sexuality | 0|none | 0|acc |0.7023|± |0.0401| | |
| | - professional_psychology | 0|none | 0|acc |0.6503|± |0.0193| | |
| | - public_relations | 0|none | 0|acc |0.6545|± |0.0455| | |
| | - security_studies | 0|none | 0|acc |0.7143|± |0.0289| | |
| | - sociology | 0|none | 0|acc |0.8060|± |0.0280| | |
| | - us_foreign_policy | 0|none | 0|acc |0.8800|± |0.0327| | |
| | - stem |N/A |none | 0|acc |0.5109|± |0.0086| | |
| | - abstract_algebra | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - anatomy | 0|none | 0|acc |0.6296|± |0.0417| | |
| | - astronomy | 0|none | 0|acc |0.6842|± |0.0378| | |
| | - college_biology | 0|none | 0|acc |0.7292|± |0.0372| | |
| | - college_chemistry | 0|none | 0|acc |0.4500|± |0.0500| | |
| | - college_computer_science | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - college_mathematics | 0|none | 0|acc |0.4300|± |0.0498| | |
| | - college_physics | 0|none | 0|acc |0.4118|± |0.0490| | |
| | - computer_security | 0|none | 0|acc |0.6900|± |0.0465| | |
| | - conceptual_physics | 0|none | 0|acc |0.4936|± |0.0327| | |
| | - electrical_engineering | 0|none | 0|acc |0.5448|± |0.0415| | |
| | - elementary_mathematics | 0|none | 0|acc |0.4206|± |0.0254| | |
| | - high_school_biology | 0|none | 0|acc |0.7032|± |0.0260| | |
| | - high_school_chemistry | 0|none | 0|acc |0.5172|± |0.0352| | |
| | - high_school_computer_science | 0|none | 0|acc |0.6500|± |0.0479| | |
| | - high_school_mathematics | 0|none | 0|acc |0.3222|± |0.0285| | |
| | - high_school_physics | 0|none | 0|acc |0.4106|± |0.0402| | |
| | - high_school_statistics | 0|none | 0|acc |0.5093|± |0.0341| | |
| | - machine_learning | 0|none | 0|acc |0.3304|± |0.0446| | |