WizardLM-2-7B-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
WizardLM-2-7B	35.76	68.56	56.46	38.24	49.76

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.65	±	2.59
		acc_norm	20.87	±	2.55
agieval_logiqa_en	0	acc	30.41	±	1.80
		acc_norm	31.34	±	1.82
agieval_lsat_ar	0	acc	21.30	±	2.71
		acc_norm	22.17	±	2.75
agieval_lsat_lr	0	acc	32.55	±	2.08
		acc_norm	35.49	±	2.12
agieval_lsat_rc	0	acc	48.33	±	3.05
		acc_norm	47.58	±	3.05
agieval_sat_en	0	acc	61.17	±	3.40
		acc_norm	62.14	±	3.39
agieval_sat_en_without_passage	0	acc	40.29	±	3.43
		acc_norm	37.86	±	3.39
agieval_sat_math	0	acc	28.64	±	3.05
		acc_norm	28.64	±	3.05

Average: 35.76%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	50.17	±	1.46
		acc_norm	51.19	±	1.46
arc_easy	0	acc	77.02	±	0.86
		acc_norm	70.96	±	0.93
boolq	1	acc	84.71	±	0.63
hellaswag	0	acc	63.43	±	0.48
		acc_norm	81.07	±	0.39
openbookqa	0	acc	32.60	±	2.10
		acc_norm	42.60	±	2.21
piqa	0	acc	78.78	±	0.95
		acc_norm	78.45	±	0.96
winogrande	0	acc	70.96	±	1.28

Average: 68.56%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	38.19	±	1.70
		mc2	56.46	±	1.58

Average: 56.46%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	54.74	±	3.62
bigbench_date_understanding	0	multiple_choice_grade	62.87	±	2.52
bigbench_disambiguation_qa	0	multiple_choice_grade	34.11	±	2.96
bigbench_geometric_shapes	0	multiple_choice_grade	17.83	±	2.02
		exact_str_match	8.91	±	1.51
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	27.40	±	2.00
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	16.86	±	1.42
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	45.00	±	2.88
bigbench_movie_recommendation	0	multiple_choice_grade	40.60	±	2.20
bigbench_navigate	0	multiple_choice_grade	50.10	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	50.70	±	1.12
bigbench_ruin_names	0	multiple_choice_grade	40.18	±	2.32
bigbench_salient_translation_error_detection	0	multiple_choice_grade	16.93	±	1.19
bigbench_snarks	0	multiple_choice_grade	53.04	±	3.72
bigbench_sports_understanding	0	multiple_choice_grade	58.42	±	1.57
bigbench_temporal_sequences	0	multiple_choice_grade	36.20	±	1.52
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	22.88	±	1.19
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	15.43	±	0.86
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	45.00	±	2.88

Average: 38.24%

Average score: 49.76%

Elapsed time: 02:23:11