GuilhermeNaturaUmana/results_2025-01-22T18-44-30.819816.json

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
mmlu	1	none		acc	_	0.8217	_	0.0031
- humanities	1	none		acc	_	0.8051	_	0.0056
- formal_logic	0	none	5	acc	_	0.6905	_	0.0413
- high_school_european_history	0	none	5	acc	_	0.8848	_	0.0249
- high_school_us_history	0	none	5	acc	_	0.9412	_	0.0165
- high_school_world_history	0	none	5	acc	_	0.9409	_	0.0153
- international_law	0	none	5	acc	_	0.9174	_	0.0251
- jurisprudence	0	none	5	acc	_	0.8889	_	0.0304
- logical_fallacies	0	none	5	acc	_	0.8834	_	0.0252
- moral_disputes	0	none	5	acc	_	0.8468	_	0.0194
- moral_scenarios	0	none	5	acc	_	0.8503	_	0.0119
- philosophy	0	none	5	acc	_	0.8424	_	0.0207
- prehistory	0	none	5	acc	_	0.8951	_	0.0171
- professional_law	0	none	5	acc	_	0.6701	_	0.0120
- world_religions	0	none	5	acc	_	0.9064	_	0.0223
- other	1	none		acc	_	0.8478	_	0.0061
- business_ethics	0	none	5	acc	_	0.8100	_	0.0394
- clinical_knowledge	0	none	5	acc	_	0.8679	_	0.0208
- college_medicine	0	none	5	acc	_	0.7688	_	0.0321
- global_facts	0	none	5	acc	_	0.5800	_	0.0496
- human_aging	0	none	5	acc	_	0.8251	_	0.0255
- management	0	none	5	acc	_	0.9223	_	0.0265
- marketing	0	none	5	acc	_	0.9402	_	0.0155
- professional_medicine	0	none	5	acc	_	0.9301	_	0.0155
- virology	0	none	5	acc	_	0.5783	_	0.0384
- social sciences	1	none		acc	_	0.8902	_	0.0056
- econometrics	0	none	5	acc	_	0.7368	_	0.0414
- high_school_geography	0	none	5	acc	_	0.9343	_	0.0176
- high_school_government_and_politics	0	none	5	acc	_	0.9741	_	0.0115
- abstract_algebra	0	none	5	acc	_	0.5600	_	0.0499
- anatomy	0	none	5	acc	_	0.8148	_	0.0336
- astronomy	0	none	5	acc	_	0.9145	_	0.0228
- college_biology	0	none	5	acc	_	0.9375	_	0.0202
- college_chemistry	0	none	5	acc	_	0.5600	_	0.0499
- college_computer_science	0	none	5	acc	_	0.6800	_	0.0469
- college_mathematics	0	none	5	acc	_	0.5700	_	0.0498
- college_physics	0	none	5	acc	_	0.6275	_	0.0481
- computer_security	0	none	5	acc	_	0.8300	_	0.0378
- conceptual_physics	0	none	5	acc	_	0.8596	_	0.0227
- electrical_engineering	0	none	5	acc	_	0.7931	_	0.0338
- elementary_mathematics	0	none	5	acc	_	0.7487	_	0.0223
- high_school_biology	0	none	5	acc	_	0.9194	_	0.0155
- high_school_chemistry	0	none	5	acc	_	0.7389	_	0.0309
- high_school_computer_science	0	none	5	acc	_	0.9000	_	0.0302
- high_school_mathematics	0	none	5	acc	_	0.5407	_	0.0304
- high_school_physics	0	none	5	acc	_	0.6490	_	0.0390
- high_school_statistics	0	none	5	acc	_	0.7546	_	0.0293
- machine_learning	0	none	5	acc	_	0.6964	_	0.0436

Groups	Version	Filter	n-shot	Metric		Value		Stderr
mmlu	1	none		acc	_	0.8217	_	0.0031
- humanities	1	none		acc	_	0.8051	_	0.0056
- other	1	none		acc	_	0.8478	_	0.0061
- social sciences	1	none		acc	_	0.8902	_	0.0056
- stem	1	none		acc	_	0.7542	_	0.0073