| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4052|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.3815|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.3651|± |0.0431| | |
| | - high_school_european_history | 0|none | 0|acc |0.5636|± |0.0387| | |
| | - high_school_us_history | 0|none | 0|acc |0.4804|± |0.0351| | |
| | - high_school_world_history | 0|none | 0|acc |0.5527|± |0.0324| | |
| | - international_law | 0|none | 0|acc |0.5537|± |0.0454| | |
| | - jurisprudence | 0|none | 0|acc |0.4907|± |0.0483| | |
| | - logical_fallacies | 0|none | 0|acc |0.4540|± |0.0391| | |
| | - moral_disputes | 0|none | 0|acc |0.3988|± |0.0264| | |
| | - moral_scenarios | 0|none | 0|acc |0.2447|± |0.0144| | |
| | - philosophy | 0|none | 0|acc |0.5048|± |0.0284| | |
| | - prehistory | 0|none | 0|acc |0.4414|± |0.0276| | |
| | - professional_law | 0|none | 0|acc |0.3110|± |0.0118| | |
| | - world_religions | 0|none | 0|acc |0.5789|± |0.0379| | |
| | - other |N/A |none | 0|acc |0.4538|± |0.0089| | |
| | - business_ethics | 0|none | 0|acc |0.4100|± |0.0494| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4491|± |0.0306| | |
| | - college_medicine | 0|none | 0|acc |0.4393|± |0.0378| | |
| | - global_facts | 0|none | 0|acc |0.2700|± |0.0446| | |
| | - human_aging | 0|none | 0|acc |0.3812|± |0.0326| | |
| | - management | 0|none | 0|acc |0.4660|± |0.0494| | |
| | - marketing | 0|none | 0|acc |0.5855|± |0.0323| | |
| | - medical_genetics | 0|none | 0|acc |0.4800|± |0.0502| | |
| | - miscellaneous | 0|none | 0|acc |0.5198|± |0.0179| | |
| | - nutrition | 0|none | 0|acc |0.4542|± |0.0285| | |
| | - professional_accounting | 0|none | 0|acc |0.3369|± |0.0282| | |
| | - professional_medicine | 0|none | 0|acc |0.4559|± |0.0303| | |
| | - virology | 0|none | 0|acc |0.3855|± |0.0379| | |
| | - social_sciences |N/A |none | 0|acc |0.4469|± |0.0088| | |
| | - econometrics | 0|none | 0|acc |0.2368|± |0.0400| | |
| | - high_school_geography | 0|none | 0|acc |0.4242|± |0.0352| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.5959|± |0.0354| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3795|± |0.0246| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3529|± |0.0310| | |
| | - high_school_psychology | 0|none | 0|acc |0.5284|± |0.0214| | |
| | - human_sexuality | 0|none | 0|acc |0.4809|± |0.0438| | |
| | - professional_psychology | 0|none | 0|acc |0.3824|± |0.0197| | |
| | - public_relations | 0|none | 0|acc |0.3818|± |0.0465| | |
| | - security_studies | 0|none | 0|acc |0.4735|± |0.0320| | |
| | - sociology | 0|none | 0|acc |0.5821|± |0.0349| | |
| | - us_foreign_policy | 0|none | 0|acc |0.5700|± |0.0498| | |
| | - stem |N/A |none | 0|acc |0.3520|± |0.0084| | |
| | - abstract_algebra | 0|none | 0|acc |0.2800|± |0.0451| | |
| | - anatomy | 0|none | 0|acc |0.4444|± |0.0429| | |
| | - astronomy | 0|none | 0|acc |0.4408|± |0.0404| | |
| | - college_biology | 0|none | 0|acc |0.4097|± |0.0411| | |
| | - college_chemistry | 0|none | 0|acc |0.4300|± |0.0498| | |
| | - college_computer_science | 0|none | 0|acc |0.3800|± |0.0488| | |
| | - college_mathematics | 0|none | 0|acc |0.3500|± |0.0479| | |
| | - college_physics | 0|none | 0|acc |0.3039|± |0.0458| | |
| | - computer_security | 0|none | 0|acc |0.4600|± |0.0501| | |
| | - conceptual_physics | 0|none | 0|acc |0.3660|± |0.0315| | |
| | - electrical_engineering | 0|none | 0|acc |0.4069|± |0.0409| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2540|± |0.0224| | |
| | - high_school_biology | 0|none | 0|acc |0.4161|± |0.0280| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3054|± |0.0324| | |
| | - high_school_computer_science | 0|none | 0|acc |0.4000|± |0.0492| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2444|± |0.0262| | |
| | - high_school_physics | 0|none | 0|acc |0.3311|± |0.0384| | |
| | - high_school_statistics | 0|none | 0|acc |0.3287|± |0.0320| | |
| | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464| | |