deepseek-moe-16b-chat-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
deepseek-moe-16b-chat	30.42	68.72	48.73	35.02	45.72

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	17.72	±	2.40
		acc_norm	17.72	±	2.40
agieval_logiqa_en	0	acc	29.34	±	1.79
		acc_norm	33.03	±	1.84
agieval_lsat_ar	0	acc	22.61	±	2.76
		acc_norm	22.61	±	2.76
agieval_lsat_lr	0	acc	33.14	±	2.09
		acc_norm	30.98	±	2.05
agieval_lsat_rc	0	acc	34.57	±	2.91
		acc_norm	29.74	±	2.79
agieval_sat_en	0	acc	52.43	±	3.49
		acc_norm	50.97	±	3.49
agieval_sat_en_without_passage	0	acc	34.95	±	3.33
		acc_norm	31.07	±	3.23
agieval_sat_math	0	acc	29.09	±	3.07
		acc_norm	27.27	±	3.01

Average: 30.42%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	49.32	±	1.46
		acc_norm	51.62	±	1.46
arc_easy	0	acc	78.28	±	0.85
		acc_norm	74.58	±	0.89
boolq	1	acc	79.79	±	0.70
hellaswag	0	acc	60.78	±	0.49
		acc_norm	78.53	±	0.41
openbookqa	0	acc	34.00	±	2.12
		acc_norm	44.20	±	2.22
piqa	0	acc	79.98	±	0.93
		acc_norm	80.36	±	0.93
winogrande	0	acc	71.98	±	1.26

Average: 68.72%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	33.54	±	1.65
		mc2	48.73	±	1.54

Average: 48.73%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	54.21	±	3.62
bigbench_date_understanding	0	multiple_choice_grade	61.79	±	2.53
bigbench_disambiguation_qa	0	multiple_choice_grade	36.43	±	3.00
bigbench_geometric_shapes	0	multiple_choice_grade	9.47	±	1.55
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	26.40	±	1.97
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	17.29	±	1.43
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	42.33	±	2.86
bigbench_movie_recommendation	0	multiple_choice_grade	37.40	±	2.17
bigbench_navigate	0	multiple_choice_grade	53.60	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	47.95	±	1.12
bigbench_ruin_names	0	multiple_choice_grade	18.30	±	1.83
bigbench_salient_translation_error_detection	0	multiple_choice_grade	24.95	±	1.37
bigbench_snarks	0	multiple_choice_grade	51.38	±	3.73
bigbench_sports_understanding	0	multiple_choice_grade	51.01	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	20.40	±	1.27
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	20.64	±	1.15
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	14.51	±	0.84
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	42.33	±	2.86

Average: 35.02%

Average score: 45.72%

Elapsed time: 03:11:24