| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.3892|± |0.0040| | |
| | - humanities |N/A |none | 0|acc |0.3766|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404| | |
| | - high_school_european_history | 0|none | 0|acc |0.4909|± |0.0390| | |
| | - high_school_us_history | 0|none | 0|acc |0.5196|± |0.0351| | |
| | - high_school_world_history | 0|none | 0|acc |0.5105|± |0.0325| | |
| | - international_law | 0|none | 0|acc |0.6364|± |0.0439| | |
| | - jurisprudence | 0|none | 0|acc |0.4074|± |0.0475| | |
| | - logical_fallacies | 0|none | 0|acc |0.4356|± |0.0390| | |
| | - moral_disputes | 0|none | 0|acc |0.4104|± |0.0265| | |
| | - moral_scenarios | 0|none | 0|acc |0.2436|± |0.0144| | |
| | - philosophy | 0|none | 0|acc |0.4277|± |0.0281| | |
| | - prehistory | 0|none | 0|acc |0.4444|± |0.0276| | |
| | - professional_law | 0|none | 0|acc |0.3259|± |0.0120| | |
| | - world_religions | 0|none | 0|acc |0.5789|± |0.0379| | |
| | - other |N/A |none | 0|acc |0.4232|± |0.0088| | |
| | - business_ethics | 0|none | 0|acc |0.4000|± |0.0492| | |
| | - clinical_knowledge | 0|none | 0|acc |0.3811|± |0.0299| | |
| | - college_medicine | 0|none | 0|acc |0.3410|± |0.0361| | |
| | - global_facts | 0|none | 0|acc |0.2700|± |0.0446| | |
| | - human_aging | 0|none | 0|acc |0.4081|± |0.0330| | |
| | - management | 0|none | 0|acc |0.4951|± |0.0495| | |
| | - marketing | 0|none | 0|acc |0.5726|± |0.0324| | |
| | - medical_genetics | 0|none | 0|acc |0.3600|± |0.0482| | |
| | - miscellaneous | 0|none | 0|acc |0.5096|± |0.0179| | |
| | - nutrition | 0|none | 0|acc |0.4346|± |0.0284| | |
| | - professional_accounting | 0|none | 0|acc |0.2979|± |0.0273| | |
| | - professional_medicine | 0|none | 0|acc |0.3456|± |0.0289| | |
| | - virology | 0|none | 0|acc |0.3976|± |0.0381| | |
| | - social_sciences |N/A |none | 0|acc |0.4374|± |0.0089| | |
| | - econometrics | 0|none | 0|acc |0.2456|± |0.0405| | |
| | - high_school_geography | 0|none | 0|acc |0.3788|± |0.0346| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.5648|± |0.0358| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.4000|± |0.0248| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3487|± |0.0310| | |
| | - high_school_psychology | 0|none | 0|acc |0.4771|± |0.0214| | |
| | - human_sexuality | 0|none | 0|acc |0.4656|± |0.0437| | |
| | - professional_psychology | 0|none | 0|acc |0.4134|± |0.0199| | |
| | - public_relations | 0|none | 0|acc |0.4455|± |0.0476| | |
| | - security_studies | 0|none | 0|acc |0.4367|± |0.0318| | |
| | - sociology | 0|none | 0|acc |0.5224|± |0.0353| | |
| | - us_foreign_policy | 0|none | 0|acc |0.6000|± |0.0492| | |
| | - stem |N/A |none | 0|acc |0.3273|± |0.0082| | |
| | - abstract_algebra | 0|none | 0|acc |0.2300|± |0.0423| | |
| | - anatomy | 0|none | 0|acc |0.4000|± |0.0423| | |
| | - astronomy | 0|none | 0|acc |0.4605|± |0.0406| | |
| | - college_biology | 0|none | 0|acc |0.3611|± |0.0402| | |
| | - college_chemistry | 0|none | 0|acc |0.2600|± |0.0441| | |
| | - college_computer_science | 0|none | 0|acc |0.3700|± |0.0485| | |
| | - college_mathematics | 0|none | 0|acc |0.2300|± |0.0423| | |
| | - college_physics | 0|none | 0|acc |0.2157|± |0.0409| | |
| | - computer_security | 0|none | 0|acc |0.5200|± |0.0502| | |
| | - conceptual_physics | 0|none | 0|acc |0.3362|± |0.0309| | |
| | - electrical_engineering | 0|none | 0|acc |0.3862|± |0.0406| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2884|± |0.0233| | |
| | - high_school_biology | 0|none | 0|acc |0.4645|± |0.0284| | |
| | - high_school_chemistry | 0|none | 0|acc |0.2709|± |0.0313| | |
| | - high_school_computer_science | 0|none | 0|acc |0.3600|± |0.0482| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2556|± |0.0266| | |
| | - high_school_physics | 0|none | 0|acc |0.2318|± |0.0345| | |
| | - high_school_statistics | 0|none | 0|acc |0.2407|± |0.0292| | |
| | - machine_learning | 0|none | 0|acc |0.3393|± |0.0449| | |