Meta-Llama-3-12B-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Meta-Llama-3-12B	29.46	68.01	41.02	35.57	43.52

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	25.98	±	2.76
		acc_norm	23.62	±	2.67
agieval_logiqa_en	0	acc	29.03	±	1.78
		acc_norm	31.80	±	1.83
agieval_lsat_ar	0	acc	20.00	±	2.64
		acc_norm	19.57	±	2.62
agieval_lsat_lr	0	acc	32.16	±	2.07
		acc_norm	28.24	±	2.00
agieval_lsat_rc	0	acc	39.78	±	2.99
		acc_norm	33.83	±	2.89
agieval_sat_en	0	acc	52.91	±	3.49
		acc_norm	41.75	±	3.44
agieval_sat_en_without_passage	0	acc	37.38	±	3.38
		acc_norm	29.13	±	3.17
agieval_sat_math	0	acc	30.91	±	3.12
		acc_norm	27.73	±	3.02

Average: 29.46%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	45.31	±	1.45
		acc_norm	48.98	±	1.46
arc_easy	0	acc	76.60	±	0.87
		acc_norm	73.06	±	0.91
boolq	1	acc	78.84	±	0.71
hellaswag	0	acc	61.00	±	0.49
		acc_norm	78.70	±	0.41
openbookqa	0	acc	35.20	±	2.14
		acc_norm	46.60	±	2.23
piqa	0	acc	78.78	±	0.95
		acc_norm	78.84	±	0.95
winogrande	0	acc	71.03	±	1.27

Average: 68.01%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	26.07	±	1.54
		mc2	41.02	±	1.43

Average: 41.02%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	53.16	±	3.63
bigbench_date_understanding	0	multiple_choice_grade	58.81	±	2.57
bigbench_disambiguation_qa	0	multiple_choice_grade	31.40	±	2.89
bigbench_geometric_shapes	0	multiple_choice_grade	20.61	±	2.14
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	24.60	±	1.93
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	16.29	±	1.40
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	38.33	±	2.81
bigbench_movie_recommendation	0	multiple_choice_grade	32.80	±	2.10
bigbench_navigate	0	multiple_choice_grade	49.50	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	46.75	±	1.12
bigbench_ruin_names	0	multiple_choice_grade	37.50	±	2.29
bigbench_salient_translation_error_detection	0	multiple_choice_grade	25.25	±	1.38
bigbench_snarks	0	multiple_choice_grade	56.35	±	3.70
bigbench_sports_understanding	0	multiple_choice_grade	49.59	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	22.00	±	1.31
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	23.04	±	1.19
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	16.00	±	0.88
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	38.33	±	2.81

Average: 35.57%

Average score: 43.52%

Elapsed time: 03:17:47