| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.3213|± |0.0039| | |
| | - humanities |N/A |none | 0|acc |0.3078|± |0.0067| | |
| | - formal_logic | 0|none | 0|acc |0.3016|± |0.0410| | |
| | - high_school_european_history | 0|none | 0|acc |0.3091|± |0.0361| | |
| | - high_school_us_history | 0|none | 0|acc |0.3922|± |0.0343| | |
| | - high_school_world_history | 0|none | 0|acc |0.3713|± |0.0315| | |
| | - international_law | 0|none | 0|acc |0.4628|± |0.0455| | |
| | - jurisprudence | 0|none | 0|acc |0.4352|± |0.0479| | |
| | - logical_fallacies | 0|none | 0|acc |0.3436|± |0.0373| | |
| | - moral_disputes | 0|none | 0|acc |0.2948|± |0.0245| | |
| | - moral_scenarios | 0|none | 0|acc |0.2391|± |0.0143| | |
| | - philosophy | 0|none | 0|acc |0.3505|± |0.0271| | |
| | - prehistory | 0|none | 0|acc |0.3580|± |0.0267| | |
| | - professional_law | 0|none | 0|acc |0.2797|± |0.0115| | |
| | - world_religions | 0|none | 0|acc |0.3626|± |0.0369| | |
| | - other |N/A |none | 0|acc |0.3450|± |0.0085| | |
| | - business_ethics | 0|none | 0|acc |0.3800|± |0.0488| | |
| | - clinical_knowledge | 0|none | 0|acc |0.3396|± |0.0291| | |
| | - college_medicine | 0|none | 0|acc |0.3006|± |0.0350| | |
| | - global_facts | 0|none | 0|acc |0.2400|± |0.0429| | |
| | - human_aging | 0|none | 0|acc |0.3318|± |0.0316| | |
| | - management | 0|none | 0|acc |0.3592|± |0.0475| | |
| | - marketing | 0|none | 0|acc |0.4103|± |0.0322| | |
| | - medical_genetics | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - miscellaneous | 0|none | 0|acc |0.3908|± |0.0174| | |
| | - nutrition | 0|none | 0|acc |0.3987|± |0.0280| | |
| | - professional_accounting | 0|none | 0|acc |0.2660|± |0.0264| | |
| | - professional_medicine | 0|none | 0|acc |0.2868|± |0.0275| | |
| | - virology | 0|none | 0|acc |0.3072|± |0.0359| | |
| | - social_sciences |N/A |none | 0|acc |0.3347|± |0.0085| | |
| | - econometrics | 0|none | 0|acc |0.2281|± |0.0395| | |
| | - high_school_geography | 0|none | 0|acc |0.2576|± |0.0312| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.3679|± |0.0348| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.2923|± |0.0231| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3109|± |0.0301| | |
| | - high_school_psychology | 0|none | 0|acc |0.3761|± |0.0208| | |
| | - human_sexuality | 0|none | 0|acc |0.3588|± |0.0421| | |
| | - professional_psychology | 0|none | 0|acc |0.3284|± |0.0190| | |
| | - public_relations | 0|none | 0|acc |0.3545|± |0.0458| | |
| | - security_studies | 0|none | 0|acc |0.3796|± |0.0311| | |
| | - sociology | 0|none | 0|acc |0.3483|± |0.0337| | |
| | - us_foreign_policy | 0|none | 0|acc |0.3900|± |0.0490| | |
| | - stem |N/A |none | 0|acc |0.3051|± |0.0081| | |
| | - abstract_algebra | 0|none | 0|acc |0.2200|± |0.0416| | |
| | - anatomy | 0|none | 0|acc |0.4000|± |0.0423| | |
| | - astronomy | 0|none | 0|acc |0.2961|± |0.0372| | |
| | - college_biology | 0|none | 0|acc |0.3681|± |0.0403| | |
| | - college_chemistry | 0|none | 0|acc |0.2300|± |0.0423| | |
| | - college_computer_science | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - college_mathematics | 0|none | 0|acc |0.1700|± |0.0378| | |
| | - college_physics | 0|none | 0|acc |0.1863|± |0.0387| | |
| | - computer_security | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - conceptual_physics | 0|none | 0|acc |0.3872|± |0.0318| | |
| | - electrical_engineering | 0|none | 0|acc |0.4069|± |0.0409| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2937|± |0.0235| | |
| | - high_school_biology | 0|none | 0|acc |0.3935|± |0.0278| | |
| | - high_school_chemistry | 0|none | 0|acc |0.2463|± |0.0303| | |
| | - high_school_computer_science | 0|none | 0|acc |0.3900|± |0.0490| | |
| | - high_school_mathematics | 0|none | 0|acc |0.1889|± |0.0239| | |
| | - high_school_physics | 0|none | 0|acc |0.3444|± |0.0388| | |
| | - high_school_statistics | 0|none | 0|acc |0.2824|± |0.0307| | |
| | - machine_learning | 0|none | 0|acc |0.2768|± |0.0425| | |