| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.4155|± |0.0041| | |
| | - humanities |N/A |none | 0|acc |0.3892|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.3571|± |0.0429| | |
| | - high_school_european_history | 0|none | 0|acc |0.6061|± |0.0382| | |
| | - high_school_us_history | 0|none | 0|acc |0.4755|± |0.0351| | |
| | - high_school_world_history | 0|none | 0|acc |0.5992|± |0.0319| | |
| | - international_law | 0|none | 0|acc |0.5950|± |0.0448| | |
| | - jurisprudence | 0|none | 0|acc |0.4722|± |0.0483| | |
| | - logical_fallacies | 0|none | 0|acc |0.4969|± |0.0393| | |
| | - moral_disputes | 0|none | 0|acc |0.4104|± |0.0265| | |
| | - moral_scenarios | 0|none | 0|acc |0.2413|± |0.0143| | |
| | - philosophy | 0|none | 0|acc |0.5177|± |0.0284| | |
| | - prehistory | 0|none | 0|acc |0.4414|± |0.0276| | |
| | - professional_law | 0|none | 0|acc |0.3149|± |0.0119| | |
| | - world_religions | 0|none | 0|acc |0.5731|± |0.0379| | |
| | - other |N/A |none | 0|acc |0.4689|± |0.0089| | |
| | - business_ethics | 0|none | 0|acc |0.4200|± |0.0496| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4755|± |0.0307| | |
| | - college_medicine | 0|none | 0|acc |0.4393|± |0.0378| | |
| | - global_facts | 0|none | 0|acc |0.3000|± |0.0461| | |
| | - human_aging | 0|none | 0|acc |0.4081|± |0.0330| | |
| | - management | 0|none | 0|acc |0.4272|± |0.0490| | |
| | - marketing | 0|none | 0|acc |0.6239|± |0.0317| | |
| | - medical_genetics | 0|none | 0|acc |0.5200|± |0.0502| | |
| | - miscellaneous | 0|none | 0|acc |0.5364|± |0.0178| | |
| | - nutrition | 0|none | 0|acc |0.4542|± |0.0285| | |
| | - professional_accounting | 0|none | 0|acc |0.3582|± |0.0286| | |
| | - professional_medicine | 0|none | 0|acc |0.4743|± |0.0303| | |
| | - virology | 0|none | 0|acc |0.3675|± |0.0375| | |
| | - social_sciences |N/A |none | 0|acc |0.4651|± |0.0089| | |
| | - econometrics | 0|none | 0|acc |0.1930|± |0.0371| | |
| | - high_school_geography | 0|none | 0|acc |0.4596|± |0.0355| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.5596|± |0.0358| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3821|± |0.0246| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3571|± |0.0311| | |
| | - high_school_psychology | 0|none | 0|acc |0.5468|± |0.0213| | |
| | - human_sexuality | 0|none | 0|acc |0.5115|± |0.0438| | |
| | - professional_psychology | 0|none | 0|acc |0.4412|± |0.0201| | |
| | - public_relations | 0|none | 0|acc |0.4273|± |0.0474| | |
| | - security_studies | 0|none | 0|acc |0.4571|± |0.0319| | |
| | - sociology | 0|none | 0|acc |0.5871|± |0.0348| | |
| | - us_foreign_policy | 0|none | 0|acc |0.6400|± |0.0482| | |
| | - stem |N/A |none | 0|acc |0.3536|± |0.0084| | |
| | - abstract_algebra | 0|none | 0|acc |0.2700|± |0.0446| | |
| | - anatomy | 0|none | 0|acc |0.4370|± |0.0428| | |
| | - astronomy | 0|none | 0|acc |0.4342|± |0.0403| | |
| | - college_biology | 0|none | 0|acc |0.4028|± |0.0410| | |
| | - college_chemistry | 0|none | 0|acc |0.3900|± |0.0490| | |
| | - college_computer_science | 0|none | 0|acc |0.3700|± |0.0485| | |
| | - college_mathematics | 0|none | 0|acc |0.3800|± |0.0488| | |
| | - college_physics | 0|none | 0|acc |0.2843|± |0.0449| | |
| | - computer_security | 0|none | 0|acc |0.5200|± |0.0502| | |
| | - conceptual_physics | 0|none | 0|acc |0.3532|± |0.0312| | |
| | - electrical_engineering | 0|none | 0|acc |0.3931|± |0.0407| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2725|± |0.0229| | |
| | - high_school_biology | 0|none | 0|acc |0.4484|± |0.0283| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3300|± |0.0331| | |
| | - high_school_computer_science | 0|none | 0|acc |0.3900|± |0.0490| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2481|± |0.0263| | |
| | - high_school_physics | 0|none | 0|acc |0.2980|± |0.0373| | |
| | - high_school_statistics | 0|none | 0|acc |0.3056|± |0.0314| | |
| | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464| | |