| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.2578|± |0.0037| | |
| | - humanities |N/A |none | 0|acc |0.2465|± |0.0063| | |
| | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404| | |
| | - high_school_european_history | 0|none | 0|acc |0.2424|± |0.0335| | |
| | - high_school_us_history | 0|none | 0|acc |0.2255|± |0.0293| | |
| | - high_school_world_history | 0|none | 0|acc |0.2489|± |0.0281| | |
| | - international_law | 0|none | 0|acc |0.1983|± |0.0364| | |
| | - jurisprudence | 0|none | 0|acc |0.2685|± |0.0428| | |
| | - logical_fallacies | 0|none | 0|acc |0.2515|± |0.0341| | |
| | - moral_disputes | 0|none | 0|acc |0.2630|± |0.0237| | |
| | - moral_scenarios | 0|none | 0|acc |0.2335|± |0.0141| | |
| | - philosophy | 0|none | 0|acc |0.2122|± |0.0232| | |
| | - prehistory | 0|none | 0|acc |0.2377|± |0.0237| | |
| | - professional_law | 0|none | 0|acc |0.2640|± |0.0113| | |
| | - world_religions | 0|none | 0|acc |0.2164|± |0.0316| | |
| | - other |N/A |none | 0|acc |0.2617|± |0.0079| | |
| | - business_ethics | 0|none | 0|acc |0.2300|± |0.0423| | |
| | - clinical_knowledge | 0|none | 0|acc |0.3019|± |0.0283| | |
| | - college_medicine | 0|none | 0|acc |0.3179|± |0.0355| | |
| | - global_facts | 0|none | 0|acc |0.1800|± |0.0386| | |
| | - human_aging | 0|none | 0|acc |0.1794|± |0.0257| | |
| | - management | 0|none | 0|acc |0.3107|± |0.0458| | |
| | - marketing | 0|none | 0|acc |0.2863|± |0.0296| | |
| | - medical_genetics | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - miscellaneous | 0|none | 0|acc |0.2401|± |0.0153| | |
| | - nutrition | 0|none | 0|acc |0.2843|± |0.0258| | |
| | - professional_accounting | 0|none | 0|acc |0.2872|± |0.0270| | |
| | - professional_medicine | 0|none | 0|acc |0.2831|± |0.0274| | |
| | - virology | 0|none | 0|acc |0.2169|± |0.0321| | |
| | - social_sciences |N/A |none | 0|acc |0.2720|± |0.0080| | |
| | - econometrics | 0|none | 0|acc |0.2193|± |0.0389| | |
| | - high_school_geography | 0|none | 0|acc |0.3030|± |0.0327| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.2798|± |0.0324| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3385|± |0.0240| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.2983|± |0.0297| | |
| | - high_school_psychology | 0|none | 0|acc |0.2807|± |0.0193| | |
| | - human_sexuality | 0|none | 0|acc |0.2595|± |0.0384| | |
| | - professional_psychology | 0|none | 0|acc |0.2288|± |0.0170| | |
| | - public_relations | 0|none | 0|acc |0.2273|± |0.0401| | |
| | - security_studies | 0|none | 0|acc |0.2571|± |0.0280| | |
| | - sociology | 0|none | 0|acc |0.2388|± |0.0301| | |
| | - us_foreign_policy | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - stem |N/A |none | 0|acc |0.2569|± |0.0078| | |
| | - abstract_algebra | 0|none | 0|acc |0.1900|± |0.0394| | |
| | - anatomy | 0|none | 0|acc |0.2444|± |0.0371| | |
| | - astronomy | 0|none | 0|acc |0.2105|± |0.0332| | |
| | - college_biology | 0|none | 0|acc |0.2917|± |0.0380| | |
| | - college_chemistry | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - college_computer_science | 0|none | 0|acc |0.2900|± |0.0456| | |
| | - college_mathematics | 0|none | 0|acc |0.2400|± |0.0429| | |
| | - college_physics | 0|none | 0|acc |0.2549|± |0.0434| | |
| | - computer_security | 0|none | 0|acc |0.2700|± |0.0446| | |
| | - conceptual_physics | 0|none | 0|acc |0.2766|± |0.0292| | |
| | - electrical_engineering | 0|none | 0|acc |0.2414|± |0.0357| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2619|± |0.0226| | |
| | - high_school_biology | 0|none | 0|acc |0.2710|± |0.0253| | |
| | - high_school_chemistry | 0|none | 0|acc |0.2167|± |0.0290| | |
| | - high_school_computer_science | 0|none | 0|acc |0.2100|± |0.0409| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2407|± |0.0261| | |
| | - high_school_physics | 0|none | 0|acc |0.2715|± |0.0363| | |
| | - high_school_statistics | 0|none | 0|acc |0.2731|± |0.0304| | |
| | - machine_learning | 0|none | 0|acc |0.2946|± |0.0433| | |