| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.3097|± |0.0039| | |
| | - humanities |N/A |none | 0|acc |0.3007|± |0.0066| | |
| | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404| | |
| | - high_school_european_history | 0|none | 0|acc |0.3515|± |0.0373| | |
| | - high_school_us_history | 0|none | 0|acc |0.3676|± |0.0338| | |
| | - high_school_world_history | 0|none | 0|acc |0.4219|± |0.0321| | |
| | - international_law | 0|none | 0|acc |0.3554|± |0.0437| | |
| | - jurisprudence | 0|none | 0|acc |0.3056|± |0.0445| | |
| | - logical_fallacies | 0|none | 0|acc |0.2761|± |0.0351| | |
| | - moral_disputes | 0|none | 0|acc |0.2948|± |0.0245| | |
| | - moral_scenarios | 0|none | 0|acc |0.2190|± |0.0138| | |
| | - philosophy | 0|none | 0|acc |0.3408|± |0.0269| | |
| | - prehistory | 0|none | 0|acc |0.3333|± |0.0262| | |
| | - professional_law | 0|none | 0|acc |0.2901|± |0.0116| | |
| | - world_religions | 0|none | 0|acc |0.3977|± |0.0375| | |
| | - other |N/A |none | 0|acc |0.3296|± |0.0084| | |
| | - business_ethics | 0|none | 0|acc |0.3500|± |0.0479| | |
| | - clinical_knowledge | 0|none | 0|acc |0.3472|± |0.0293| | |
| | - college_medicine | 0|none | 0|acc |0.2717|± |0.0339| | |
| | - global_facts | 0|none | 0|acc |0.2600|± |0.0441| | |
| | - human_aging | 0|none | 0|acc |0.2691|± |0.0298| | |
| | - management | 0|none | 0|acc |0.3107|± |0.0458| | |
| | - marketing | 0|none | 0|acc |0.4103|± |0.0322| | |
| | - medical_genetics | 0|none | 0|acc |0.2800|± |0.0451| | |
| | - miscellaneous | 0|none | 0|acc |0.3563|± |0.0171| | |
| | - nutrition | 0|none | 0|acc |0.3497|± |0.0273| | |
| | - professional_accounting | 0|none | 0|acc |0.2872|± |0.0270| | |
| | - professional_medicine | 0|none | 0|acc |0.3676|± |0.0293| | |
| | - virology | 0|none | 0|acc |0.2470|± |0.0336| | |
| | - social_sciences |N/A |none | 0|acc |0.3195|± |0.0084| | |
| | - econometrics | 0|none | 0|acc |0.2456|± |0.0405| | |
| | - high_school_geography | 0|none | 0|acc |0.3182|± |0.0332| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.3627|± |0.0347| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3026|± |0.0233| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.2395|± |0.0277| | |
| | - high_school_psychology | 0|none | 0|acc |0.3193|± |0.0200| | |
| | - human_sexuality | 0|none | 0|acc |0.3969|± |0.0429| | |
| | - professional_psychology | 0|none | 0|acc |0.2810|± |0.0182| | |
| | - public_relations | 0|none | 0|acc |0.3273|± |0.0449| | |
| | - security_studies | 0|none | 0|acc |0.3306|± |0.0301| | |
| | - sociology | 0|none | 0|acc |0.4378|± |0.0351| | |
| | - us_foreign_policy | 0|none | 0|acc |0.4400|± |0.0499| | |
| | - stem |N/A |none | 0|acc |0.2940|± |0.0081| | |
| | - abstract_algebra | 0|none | 0|acc |0.2400|± |0.0429| | |
| | - anatomy | 0|none | 0|acc |0.3556|± |0.0414| | |
| | - astronomy | 0|none | 0|acc |0.3487|± |0.0388| | |
| | - college_biology | 0|none | 0|acc |0.3542|± |0.0400| | |
| | - college_chemistry | 0|none | 0|acc |0.2600|± |0.0441| | |
| | - college_computer_science | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - college_mathematics | 0|none | 0|acc |0.3000|± |0.0461| | |
| | - college_physics | 0|none | 0|acc |0.2059|± |0.0402| | |
| | - computer_security | 0|none | 0|acc |0.3700|± |0.0485| | |
| | - conceptual_physics | 0|none | 0|acc |0.2511|± |0.0283| | |
| | - electrical_engineering | 0|none | 0|acc |0.3034|± |0.0383| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2328|± |0.0218| | |
| | - high_school_biology | 0|none | 0|acc |0.3548|± |0.0272| | |
| | - high_school_chemistry | 0|none | 0|acc |0.2365|± |0.0299| | |
| | - high_school_computer_science | 0|none | 0|acc |0.3100|± |0.0465| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2926|± |0.0277| | |
| | - high_school_physics | 0|none | 0|acc |0.3113|± |0.0378| | |
| | - high_school_statistics | 0|none | 0|acc |0.3056|± |0.0314| | |
| | - machine_learning | 0|none | 0|acc |0.2857|± |0.0429| | |