| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4794|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.4555|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404| | |
| | - high_school_european_history | 0|none | 0|acc |0.6182|± |0.0379| | |
| | - high_school_us_history | 0|none | 0|acc |0.6863|± |0.0326| | |
| | - high_school_world_history | 0|none | 0|acc |0.6456|± |0.0311| | |
| | - international_law | 0|none | 0|acc |0.6364|± |0.0439| | |
| | - jurisprudence | 0|none | 0|acc |0.6019|± |0.0473| | |
| | - logical_fallacies | 0|none | 0|acc |0.5092|± |0.0393| | |
| | - moral_disputes | 0|none | 0|acc |0.4682|± |0.0269| | |
| | - moral_scenarios | 0|none | 0|acc |0.2492|± |0.0145| | |
| | - philosophy | 0|none | 0|acc |0.5949|± |0.0279| | |
| | - prehistory | 0|none | 0|acc |0.6049|± |0.0272| | |
| | - professional_law | 0|none | 0|acc |0.3911|± |0.0125| | |
| | - world_religions | 0|none | 0|acc |0.7076|± |0.0349| | |
| | - other |N/A |none | 0|acc |0.5372|± |0.0088| | |
| | - business_ethics | 0|none | 0|acc |0.5200|± |0.0502| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4302|± |0.0305| | |
| | - college_medicine | 0|none | 0|acc |0.4451|± |0.0379| | |
| | - global_facts | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - human_aging | 0|none | 0|acc |0.5650|± |0.0333| | |
| | - management | 0|none | 0|acc |0.6214|± |0.0480| | |
| | - marketing | 0|none | 0|acc |0.6966|± |0.0301| | |
| | - medical_genetics | 0|none | 0|acc |0.5000|± |0.0503| | |
| | - miscellaneous | 0|none | 0|acc |0.6539|± |0.0170| | |
| | - nutrition | 0|none | 0|acc |0.4967|± |0.0286| | |
| | - professional_accounting | 0|none | 0|acc |0.4043|± |0.0293| | |
| | - professional_medicine | 0|none | 0|acc |0.5110|± |0.0304| | |
| | - virology | 0|none | 0|acc |0.4398|± |0.0386| | |
| | - social_sciences |N/A |none | 0|acc |0.5522|± |0.0088| | |
| | - econometrics | 0|none | 0|acc |0.2105|± |0.0384| | |
| | - high_school_geography | 0|none | 0|acc |0.5455|± |0.0355| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.7047|± |0.0329| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.4615|± |0.0253| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.4874|± |0.0325| | |
| | - high_school_psychology | 0|none | 0|acc |0.6275|± |0.0207| | |
| | - human_sexuality | 0|none | 0|acc |0.5954|± |0.0430| | |
| | - professional_psychology | 0|none | 0|acc |0.5033|± |0.0202| | |
| | - public_relations | 0|none | 0|acc |0.5273|± |0.0478| | |
| | - security_studies | 0|none | 0|acc |0.5837|± |0.0316| | |
| | - sociology | 0|none | 0|acc |0.6716|± |0.0332| | |
| | - us_foreign_policy | 0|none | 0|acc |0.7100|± |0.0456| | |
| | - stem |N/A |none | 0|acc |0.3873|± |0.0085| | |
| | - abstract_algebra | 0|none | 0|acc |0.2700|± |0.0446| | |
| | - anatomy | 0|none | 0|acc |0.4667|± |0.0431| | |
| | - astronomy | 0|none | 0|acc |0.5000|± |0.0407| | |
| | - college_biology | 0|none | 0|acc |0.4931|± |0.0418| | |
| | - college_chemistry | 0|none | 0|acc |0.4000|± |0.0492| | |
| | - college_computer_science | 0|none | 0|acc |0.4200|± |0.0496| | |
| | - college_mathematics | 0|none | 0|acc |0.2800|± |0.0451| | |
| | - college_physics | 0|none | 0|acc |0.3039|± |0.0458| | |
| | - computer_security | 0|none | 0|acc |0.6400|± |0.0482| | |
| | - conceptual_physics | 0|none | 0|acc |0.3702|± |0.0316| | |
| | - electrical_engineering | 0|none | 0|acc |0.4828|± |0.0416| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2910|± |0.0234| | |
| | - high_school_biology | 0|none | 0|acc |0.5710|± |0.0282| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3498|± |0.0336| | |
| | - high_school_computer_science | 0|none | 0|acc |0.4300|± |0.0498| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2593|± |0.0267| | |
| | - high_school_physics | 0|none | 0|acc |0.2781|± |0.0366| | |
| | - high_school_statistics | 0|none | 0|acc |0.3657|± |0.0328| | |
| | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420| | |