GuilhermeNaturaUmana/results_2025-01-29T22-15-10.400865.json

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
mmlu	2	none		acc	_	0.8211	_	0.0031
- humanities	2	none		acc	_	0.8040	_	0.0056
- formal_logic	1	none	5	acc	_	0.6825	_	0.0416
- high_school_european_history	1	none	5	acc	_	0.8788	_	0.0255
- high_school_us_history	1	none	5	acc	_	0.9461	_	0.0159
- high_school_world_history	1	none	5	acc	_	0.9409	_	0.0153
- international_law	1	none	5	acc	_	0.9091	_	0.0262
- jurisprudence	1	none	5	acc	_	0.8981	_	0.0292
- logical_fallacies	1	none	5	acc	_	0.8712	_	0.0263
- moral_disputes	1	none	5	acc	_	0.8497	_	0.0192
- moral_scenarios	1	none	5	acc	_	0.8503	_	0.0119
- philosophy	1	none	5	acc	_	0.8328	_	0.0212
- prehistory	1	none	5	acc	_	0.8951	_	0.0171
- professional_law	1	none	5	acc	_	0.6695	_	0.0120
- world_religions	1	none	5	acc	_	0.9123	_	0.0217
- other	2	none		acc	_	0.8458	_	0.0062
- business_ethics	1	none	5	acc	_	0.8000	_	0.0402
- clinical_knowledge	1	none	5	acc	_	0.8717	_	0.0206
- college_medicine	1	none	5	acc	_	0.7688	_	0.0321
- global_facts	1	none	5	acc	_	0.5800	_	0.0496
- human_aging	1	none	5	acc	_	0.8296	_	0.0252
- management	1	none	5	acc	_	0.9126	_	0.0280
- marketing	1	none	5	acc	_	0.9402	_	0.0155
- medical_genetics	1	none	5	acc	_	0.9400	_	0.0239
- miscellaneous	1	none	5	acc	_	0.9195	_	0.0097
- nutrition	1	none	5	acc	_	0.8922	_	0.0178
- professional_accounting	1	none	5	acc	_	0.6844	_	0.0277
- professional_medicine	1	none	5	acc	_	0.9265	_	0.0159
- virology	1	none	5	acc	_	0.5723	_	0.0385
- social sciences	2	none		acc	_	0.8911	_	0.0055
- econometrics	1	none	5	acc	_	0.7368	_	0.0414
- high_school_geography	1	none	5	acc	_	0.9343	_	0.0176
- human_sexuality	1	none	5	acc	_	0.8931	_	0.0271
- professional_psychology	1	none	5	acc	_	0.8627	_	0.0139
- public_relations	1	none	5	acc	_	0.7364	_	0.0422
- security_studies	1	none	5	acc	_	0.8449	_	0.0232
- college_physics	1	none	5	acc	_	0.6275	_	0.0481
- electrical_engineering	1	none	5	acc	_	0.8069	_	0.0329
- elementary_mathematics	1	none	5	acc	_	0.7540	_	0.0222
- high_school_biology	1	none	5	acc	_	0.9161	_	0.0158
- high_school_chemistry	1	none	5	acc	_	0.7192	_	0.0316
- high_school_computer_science	1	none	5	acc	_	0.9000	_	0.0302
- high_school_mathematics	1	none	5	acc	_	0.5333	_	0.0304
- high_school_physics	1	none	5	acc	_	0.6556	_	0.0388
- high_school_statistics	1	none	5	acc	_	0.7685	_	0.0288
- machine_learning	1	none	5	acc	_	0.6786	_	0.0443

Groups	Version	Filter	n-shot	Metric		Value		Stderr
mmlu	2	none		acc	_	0.8211	_	0.0031
- humanities	2	none		acc	_	0.8040	_	0.0056
- other	2	none		acc	_	0.8458	_	0.0062
- social sciences	2	none		acc	_	0.8911	_	0.0055
- stem	2	none		acc	_	0.7539	_	0.0073