README.md

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
arc_challenge	1	none	25	acc	0.1741	±	0.0111
		none	25	acc_norm	0.2014	±	0.0117
truthfulqa_mc2	2	none	0	acc	0.4726	±	0.0156
winogrande	1	none	5	acc	0.4964	±	0.0141
hellaswag	1	none	10	acc	0.2725	±	0.0044
		none	10	acc_norm	0.2794	±	0.0045
0.2563298245614035

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
abstract_algebra	0	none	5	acc	0.2900	±	0.0456
anatomy	0	none	5	acc	0.2815	±	0.0389
astronomy	0	none	5	acc	0.1776	±	0.0311
business_ethics	0	none	5	acc	0.1700	±	0.0378
clinical_knowledge	0	none	5	acc	0.2113	±	0.0251
college_biology	0	none	5	acc	0.2292	±	0.0351
college_chemistry	0	none	5	acc	0.1800	±	0.0386
college_computer_science	0	none	5	acc	0.3000	±	0.0461
college_mathematics	0	none	5	acc	0.2800	±	0.0451
college_medicine	0	none	5	acc	0.2023	±	0.0306
college_physics	0	none	5	acc	0.2451	±	0.0428
computer_security	0	none	5	acc	0.2800	±	0.0451
conceptual_physics	0	none	5	acc	0.2723	±	0.0291
econometrics	0	none	5	acc	0.2456	±	0.0405
electrical_engineering	0	none	5	acc	0.2207	±	0.0346
elementary_mathematics	0	none	5	acc	0.2540	±	0.0224
formal_logic	0	none	5	acc	0.1587	±	0.0327
global_facts	0	none	5	acc	0.2200	±	0.0416
high_school_biology	0	none	5	acc	0.2161	±	0.0234
high_school_chemistry	0	none	5	acc	0.2808	±	0.0316
high_school_computer_science	0	none	5	acc	0.2000	±	0.0402
high_school_european_history	0	none	5	acc	0.2303	±	0.0329
high_school_geography	0	none	5	acc	0.2828	±	0.0321
high_school_government_and_politics	0	none	5	acc	0.2539	±	0.0314
high_school_macroeconomics	0	none	5	acc	0.3282	±	0.0238
high_school_mathematics	0	none	5	acc	0.2630	±	0.0268
high_school_microeconomics	0	none	5	acc	0.3487	±	0.0310
high_school_physics	0	none	5	acc	0.3245	±	0.0382
high_school_psychology	0	none	5	acc	0.2514	±	0.0186
high_school_statistics	0	none	5	acc	0.4722	±	0.0340
high_school_us_history	0	none	5	acc	0.3039	±	0.0323
high_school_world_history	0	none	5	acc	0.2616	±	0.0286
human_aging	0	none	5	acc	0.2377	±	0.0286
human_sexuality	0	none	5	acc	0.2672	±	0.0388
international_law	0	none	5	acc	0.2397	±	0.0390
jurisprudence	0	none	5	acc	0.2593	±	0.0424
logical_fallacies	0	none	5	acc	0.2331	±	0.0332
machine_learning	0	none	5	acc	0.3214	±	0.0443
management	0	none	5	acc	0.1748	±	0.0376
marketing	0	none	5	acc	0.2265	±	0.0274
medical_genetics	0	none	5	acc	0.3000	±	0.0461
miscellaneous	0	none	5	acc	0.2401	±	0.0153
moral_disputes	0	none	5	acc	0.2399	±	0.0230
moral_scenarios	0	none	5	acc	0.2358	±	0.0142
nutrition	0	none	5	acc	0.2320	±	0.0242
philosophy	0	none	5	acc	0.2026	±	0.0228
prehistory	0	none	5	acc	0.2284	±	0.0234
professional_accounting	0	none	5	acc	0.2376	±	0.0254
professional_law	0	none	5	acc	0.2379	±	0.0109
professional_medicine	0	none	5	acc	0.4412	±	0.0302
professional_psychology	0	none	5	acc	0.2500	±	0.0175
public_relations	0	none	5	acc	0.1818	±	0.0369
security_studies	0	none	5	acc	0.3429	±	0.0304
sociology	0	none	5	acc	0.2438	±	0.0304
us_foreign_policy	0	none	5	acc	0.2900	±	0.0456
virology	0	none	5	acc	0.2892	±	0.0353
world_religions	0	none	5	acc	0.2222	±	0.0319