Intel/Qwen3-8B-w2g64-for-ut

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
mmlu	2	none		acc		0.6046	±	0.0039
- humanities	2	none	0	acc	↑	0.5305	±	0.0069
- formal_logic	1	none	0	acc	↑	0.4444	±	0.0444
- high_school_european_history	1	none	0	acc	↑	0.7394	±	0.0343
- high_school_us_history	1	none	0	acc	↑	0.7402	±	0.0308
- high_school_world_history	1	none	0	acc	↑	0.7764	±	0.0271
- international_law	1	none	0	acc	↑	0.7686	±	0.0385
- jurisprudence	1	none	0	acc	↑	0.6852	±	0.0449
- logical_fallacies	1	none	0	acc	↑	0.7055	±	0.0358
- moral_disputes	1	none	0	acc	↑	0.6301	±	0.0260
- moral_scenarios	1	none	0	acc	↑	0.2804	±	0.0150
- philosophy	1	none	0	acc	↑	0.6785	±	0.0265
- prehistory	1	none	0	acc	↑	0.6698	±	0.0262
- professional_law	1	none	0	acc	↑	0.4485	±	0.0127
- world_religions	1	none	0	acc	↑	0.6784	±	0.0358
- other	2	none	0	acc	↑	0.6633	±	0.0082
- business_ethics	1	none	0	acc	↑	0.6700	±	0.0473
- clinical_knowledge	1	none	0	acc	↑	0.6604	±	0.0291
- college_medicine	1	none	0	acc	↑	0.6069	±	0.0372
- global_facts	1	none	0	acc	↑	0.3700	±	0.0485
- human_aging	1	none	0	acc	↑	0.6816	±	0.0313
- management	1	none	0	acc	↑	0.7476	±	0.0430
- marketing	1	none	0	acc	↑	0.8291	±	0.0247
- medical_genetics	1	none	0	acc	↑	0.7600	±	0.0429
- miscellaneous	1	none	0	acc	↑	0.7599	±	0.0153
- nutrition	1	none	0	acc	↑	0.6699	±	0.0269
- professional_accounting	1	none	0	acc	↑	0.4610	±	0.0297
- professional_medicine	1	none	0	acc	↑	0.6176	±	0.0295
- virology	1	none	0	acc	↑	0.4819	±	0.0389
- social sciences	2	none	0	acc	↑	0.6974	±	0.0081
- econometrics	1	none	0	acc	↑	0.4737	±	0.0470
- high_school_geography	1	none	0	acc	↑	0.7172	±	0.0321
- high_school_government_and_politics	1	none	0	acc	↑	0.7720	±	0.0303
- high_school_macroeconomics	1	none	0	acc	↑	0.6128	±	0.0247
- high_school_microeconomics	1	none	0	acc	↑	0.7143	±	0.0293
- high_school_psychology	1	none	0	acc	↑	0.8128	±	0.0167
- human_sexuality	1	none	0	acc	↑	0.7176	±	0.0395
- professional_psychology	1	none	0	acc	↑	0.6127	±	0.0197
- public_relations	1	none	0	acc	↑	0.6091	±	0.0467
- security_studies	1	none	0	acc	↑	0.7551	±	0.0275
- sociology	1	none	0	acc	↑	0.7413	±	0.0310
- us_foreign_policy	1	none	0	acc	↑	0.7900	±	0.0409
- stem	2	none	0	acc	↑	0.5668	±	0.0085
- abstract_algebra	1	none	0	acc	↑	0.4400	±	0.0499
- anatomy	1	none	0	acc	↑	0.5852	±	0.0426
- astronomy	1	none	0	acc	↑	0.7039	±	0.0372
- college_biology	1	none	0	acc	↑	0.7292	±	0.0372
- college_chemistry	1	none	0	acc	↑	0.4200	±	0.0496
- college_computer_science	1	none	0	acc	↑	0.5700	±	0.0498
- college_mathematics	1	none	0	acc	↑	0.4100	±	0.0494
- college_physics	1	none	0	acc	↑	0.3431	±	0.0472
- computer_security	1	none	0	acc	↑	0.7400	±	0.0441
- conceptual_physics	1	none	0	acc	↑	0.5957	±	0.0321
- electrical_engineering	1	none	0	acc	↑	0.5586	±	0.0414
- elementary_mathematics	1	none	0	acc	↑	0.5741	±	0.0255
- high_school_biology	1	none	0	acc	↑	0.7839	±	0.0234
- high_school_chemistry	1	none	0	acc	↑	0.5714	±	0.0348
- high_school_computer_science	1	none	0	acc	↑	0.7400	±	0.0441
- high_school_mathematics	1	none	0	acc	↑	0.3667	±	0.0294
- high_school_physics	1	none	0	acc	↑	0.4768	±	0.0408
- high_school_statistics	1	none	0	acc	↑	0.5231	±	0.0341
- machine_learning	1	none	0	acc	↑	0.4286	±	0.0470
gsm8k	3	flexible-extract	5	exact_match	↑	0.6285	±	0.0133
		strict-match	5	exact_match	↑	0.6270	±	0.0133