Phi-3-mini-4k-instruct-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Phi-3-mini-4k-instruct	44.44	71.88	57.77	41.9	54

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	29.13	±	2.86
		acc_norm	28.74	±	2.85
agieval_logiqa_en	0	acc	42.86	±	1.94
		acc_norm	44.39	±	1.95
agieval_lsat_ar	0	acc	20.00	±	2.64
		acc_norm	21.74	±	2.73
agieval_lsat_lr	0	acc	52.55	±	2.21
		acc_norm	49.80	±	2.22
agieval_lsat_rc	0	acc	60.59	±	2.98
		acc_norm	58.74	±	3.01
agieval_sat_en	0	acc	76.21	±	2.97
		acc_norm	76.21	±	2.97
agieval_sat_en_without_passage	0	acc	45.63	±	3.48
		acc_norm	42.23	±	3.45
agieval_sat_math	0	acc	39.55	±	3.30
		acc_norm	33.64	±	3.19

Average: 44.44%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	55.46	±	1.45
		acc_norm	57.59	±	1.44
arc_easy	0	acc	83.21	±	0.77
		acc_norm	80.18	±	0.82
boolq	1	acc	86.24	±	0.60
hellaswag	0	acc	60.57	±	0.49
		acc_norm	78.45	±	0.41
openbookqa	0	acc	38.60	±	2.18
		acc_norm	46.80	±	2.23
piqa	0	acc	80.30	±	0.93
		acc_norm	80.25	±	0.93
winogrande	0	acc	73.64	±	1.24

Average: 71.88%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	39.17	±	1.71
		mc2	57.77	±	1.54

Average: 57.77%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	55.79	±	3.61
bigbench_date_understanding	0	multiple_choice_grade	66.12	±	2.47
bigbench_disambiguation_qa	0	multiple_choice_grade	30.62	±	2.88
bigbench_geometric_shapes	0	multiple_choice_grade	13.65	±	1.81
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	32.00	±	2.09
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	18.14	±	1.46
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	49.33	±	2.89
bigbench_movie_recommendation	0	multiple_choice_grade	26.00	±	1.96
bigbench_navigate	0	multiple_choice_grade	58.70	±	1.56
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	70.10	±	1.02
bigbench_ruin_names	0	multiple_choice_grade	40.18	±	2.32
bigbench_salient_translation_error_detection	0	multiple_choice_grade	27.45	±	1.41
bigbench_snarks	0	multiple_choice_grade	71.27	±	3.37
bigbench_sports_understanding	0	multiple_choice_grade	59.63	±	1.56
bigbench_temporal_sequences	0	multiple_choice_grade	52.10	±	1.58
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	18.80	±	1.11
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	14.91	±	0.85
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	49.33	±	2.89

Average: 41.9%

Average score: 54.0%

Elapsed time: 00:58:43