phi-2-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
phi-2	27.98	70.8	44.43	35.21	44.61

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	20.87	±	2.55
		acc_norm	22.05	±	2.61
agieval_logiqa_en	0	acc	25.65	±	1.71
		acc_norm	32.26	±	1.83
agieval_lsat_ar	0	acc	22.17	±	2.75
		acc_norm	20.43	±	2.66
agieval_lsat_lr	0	acc	29.02	±	2.01
		acc_norm	28.63	±	2.00
agieval_lsat_rc	0	acc	28.25	±	2.75
		acc_norm	28.62	±	2.76
agieval_sat_en	0	acc	49.03	±	3.49
		acc_norm	34.95	±	3.33
agieval_sat_en_without_passage	0	acc	39.32	±	3.41
		acc_norm	29.61	±	3.19
agieval_sat_math	0	acc	30.91	±	3.12
		acc_norm	27.27	±	3.01

Average: 27.98%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	53.07	±	1.46
		acc_norm	54.01	±	1.46
arc_easy	0	acc	79.88	±	0.82
		acc_norm	78.37	±	0.84
boolq	1	acc	83.36	±	0.65
hellaswag	0	acc	55.80	±	0.50
		acc_norm	73.72	±	0.44
openbookqa	0	acc	40.40	±	2.20
		acc_norm	51.40	±	2.24
piqa	0	acc	78.78	±	0.95
		acc_norm	79.27	±	0.95
winogrande	0	acc	75.45	±	1.21

Average: 70.8%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	30.84	±	1.62
		mc2	44.43	±	1.51

Average: 44.43%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	54.21	±	3.62
bigbench_date_understanding	0	multiple_choice_grade	59.35	±	2.56
bigbench_disambiguation_qa	0	multiple_choice_grade	36.82	±	3.01
bigbench_geometric_shapes	0	multiple_choice_grade	10.03	±	1.59
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	23.40	±	1.90
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	17.00	±	1.42
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	40.33	±	2.84
bigbench_movie_recommendation	0	multiple_choice_grade	41.40	±	2.20
bigbench_navigate	0	multiple_choice_grade	50.30	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	52.15	±	1.12
bigbench_ruin_names	0	multiple_choice_grade	27.46	±	2.11
bigbench_salient_translation_error_detection	0	multiple_choice_grade	25.25	±	1.38
bigbench_snarks	0	multiple_choice_grade	58.56	±	3.67
bigbench_sports_understanding	0	multiple_choice_grade	50.71	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	15.60	±	1.15
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	18.16	±	1.09
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	12.69	±	0.80
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	40.33	±	2.84

Average: 35.21%

Average score: 44.61% Elapsed time: 03:23:31