| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.6053|± |0.0039| | |
| | - humanities |N/A |none | 0|acc |0.5439|± |0.0067| | |
| | - formal_logic | 0|none | 0|acc |0.4365|± |0.0444| | |
| | - high_school_european_history | 0|none | 0|acc |0.6909|± |0.0361| | |
| | - high_school_us_history | 0|none | 0|acc |0.7892|± |0.0286| | |
| | - high_school_world_history | 0|none | 0|acc |0.8228|± |0.0249| | |
| | - international_law | 0|none | 0|acc |0.7686|± |0.0385| | |
| | - jurisprudence | 0|none | 0|acc |0.7500|± |0.0419| | |
| | - logical_fallacies | 0|none | 0|acc |0.7178|± |0.0354| | |
| | - moral_disputes | 0|none | 0|acc |0.6734|± |0.0252| | |
| | - moral_scenarios | 0|none | 0|acc |0.2380|± |0.0142| | |
| | - philosophy | 0|none | 0|acc |0.7074|± |0.0258| | |
| | - prehistory | 0|none | 0|acc |0.6975|± |0.0256| | |
| | - professional_law | 0|none | 0|acc |0.4648|± |0.0127| | |
| | - world_religions | 0|none | 0|acc |0.8070|± |0.0303| | |
| | - other |N/A |none | 0|acc |0.6917|± |0.0080| | |
| | - business_ethics | 0|none | 0|acc |0.5400|± |0.0501| | |
| | - clinical_knowledge | 0|none | 0|acc |0.7321|± |0.0273| | |
| | - college_medicine | 0|none | 0|acc |0.6243|± |0.0369| | |
| | - global_facts | 0|none | 0|acc |0.3900|± |0.0490| | |
| | - human_aging | 0|none | 0|acc |0.6637|± |0.0317| | |
| | - management | 0|none | 0|acc |0.8350|± |0.0368| | |
| | - marketing | 0|none | 0|acc |0.8590|± |0.0228| | |
| | - medical_genetics | 0|none | 0|acc |0.8300|± |0.0378| | |
| | - miscellaneous | 0|none | 0|acc |0.7982|± |0.0144| | |
| | - nutrition | 0|none | 0|acc |0.7190|± |0.0257| | |
| | - professional_accounting | 0|none | 0|acc |0.4610|± |0.0297| | |
| | - professional_medicine | 0|none | 0|acc |0.6397|± |0.0292| | |
| | - virology | 0|none | 0|acc |0.5241|± |0.0389| | |
| | - social_sciences |N/A |none | 0|acc |0.7039|± |0.0080| | |
| | - econometrics | 0|none | 0|acc |0.3421|± |0.0446| | |
| | - high_school_geography | 0|none | 0|acc |0.7576|± |0.0305| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.8290|± |0.0272| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.6179|± |0.0246| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.6639|± |0.0307| | |
| | - high_school_psychology | 0|none | 0|acc |0.8018|± |0.0171| | |
| | - human_sexuality | 0|none | 0|acc |0.7481|± |0.0381| | |
| | - professional_psychology | 0|none | 0|acc |0.6503|± |0.0193| | |
| | - public_relations | 0|none | 0|acc |0.6273|± |0.0463| | |
| | - security_studies | 0|none | 0|acc |0.7102|± |0.0290| | |
| | - sociology | 0|none | 0|acc |0.7861|± |0.0290| | |
| | - us_foreign_policy | 0|none | 0|acc |0.8400|± |0.0368| | |
| | - stem |N/A |none | 0|acc |0.5157|± |0.0086| | |
| | - abstract_algebra | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - anatomy | 0|none | 0|acc |0.6296|± |0.0417| | |
| | - astronomy | 0|none | 0|acc |0.7171|± |0.0367| | |
| | - college_biology | 0|none | 0|acc |0.7569|± |0.0359| | |
| | - college_chemistry | 0|none | 0|acc |0.4100|± |0.0494| | |
| | - college_computer_science | 0|none | 0|acc |0.4900|± |0.0502| | |
| | - college_mathematics | 0|none | 0|acc |0.3700|± |0.0485| | |
| | - college_physics | 0|none | 0|acc |0.3824|± |0.0484| | |
| | - computer_security | 0|none | 0|acc |0.7300|± |0.0446| | |
| | - conceptual_physics | 0|none | 0|acc |0.5021|± |0.0327| | |
| | - electrical_engineering | 0|none | 0|acc |0.5655|± |0.0413| | |
| | - elementary_mathematics | 0|none | 0|acc |0.4259|± |0.0255| | |
| | - high_school_biology | 0|none | 0|acc |0.7387|± |0.0250| | |
| | - high_school_chemistry | 0|none | 0|acc |0.5123|± |0.0352| | |
| | - high_school_computer_science | 0|none | 0|acc |0.6200|± |0.0488| | |
| | - high_school_mathematics | 0|none | 0|acc |0.3407|± |0.0289| | |
| | - high_school_physics | 0|none | 0|acc |0.4106|± |0.0402| | |
| | - high_school_statistics | 0|none | 0|acc |0.4676|± |0.0340| | |
| | - machine_learning | 0|none | 0|acc |0.3661|± |0.0457| | |