zephyr-7b-beta-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
zephyr-7b-beta	37.33	71.83	55.1	39.7	50.99

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.26	±	2.57
		acc_norm	20.47	±	2.54
agieval_logiqa_en	0	acc	33.33	±	1.85
		acc_norm	35.48	±	1.88
agieval_lsat_ar	0	acc	23.04	±	2.78
		acc_norm	23.91	±	2.82
agieval_lsat_lr	0	acc	41.76	±	2.19
		acc_norm	40.20	±	2.17
agieval_lsat_rc	0	acc	48.70	±	3.05
		acc_norm	46.10	±	3.04
agieval_sat_en	0	acc	60.19	±	3.42
		acc_norm	59.71	±	3.43
agieval_sat_en_without_passage	0	acc	45.63	±	3.48
		acc_norm	43.20	±	3.46
agieval_sat_math	0	acc	31.82	±	3.15
		acc_norm	29.55	±	3.08

Average: 37.33%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	57.17	±	1.45
		acc_norm	60.15	±	1.43
arc_easy	0	acc	81.36	±	0.80
		acc_norm	79.00	±	0.84
boolq	1	acc	84.95	±	0.63
hellaswag	0	acc	63.96	±	0.48
		acc_norm	82.10	±	0.38
openbookqa	0	acc	32.60	±	2.10
		acc_norm	42.80	±	2.21
piqa	0	acc	81.12	±	0.91
		acc_norm	81.28	±	0.91
winogrande	0	acc	72.53	±	1.25

Average: 71.83%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	38.8	±	1.71
		mc2	55.1	±	1.58

Average: 55.1%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	57.89	±	3.59
bigbench_date_understanding	0	multiple_choice_grade	70.73	±	2.37
bigbench_disambiguation_qa	0	multiple_choice_grade	50.00	±	3.12
bigbench_geometric_shapes	0	multiple_choice_grade	18.66	±	2.06
		exact_str_match	6.69	±	1.32
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	24.60	±	1.93
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	18.00	±	1.45
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	44.00	±	2.87
bigbench_movie_recommendation	0	multiple_choice_grade	31.00	±	2.07
bigbench_navigate	0	multiple_choice_grade	54.80	±	1.57
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	65.00	±	1.07
bigbench_ruin_names	0	multiple_choice_grade	31.47	±	2.20
bigbench_salient_translation_error_detection	0	multiple_choice_grade	22.04	±	1.31
bigbench_snarks	0	multiple_choice_grade	52.49	±	3.72
bigbench_sports_understanding	0	multiple_choice_grade	59.13	±	1.57
bigbench_temporal_sequences	0	multiple_choice_grade	31.40	±	1.47
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	22.64	±	1.18
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	16.69	±	0.89
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	44.00	±	2.87

Average: 39.7%

Average score: 50.99%