OpenHermes-2.5-neural-chat-v3-3-Slerp-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
OpenHermes-2.5-neural-chat-v3-3-Slerp	43.5	74.88	63.22	47.5	57.27

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	23.23	±	2.65
		acc_norm	22.44	±	2.62
agieval_logiqa_en	0	acc	38.86	±	1.91
		acc_norm	39.32	±	1.92
agieval_lsat_ar	0	acc	21.74	±	2.73
		acc_norm	21.30	±	2.71
agieval_lsat_lr	0	acc	50.00	±	2.22
		acc_norm	51.37	±	2.22
agieval_lsat_rc	0	acc	60.22	±	2.99
		acc_norm	59.48	±	3.00
agieval_sat_en	0	acc	75.73	±	2.99
		acc_norm	75.73	±	2.99
agieval_sat_en_without_passage	0	acc	45.63	±	3.48
		acc_norm	45.15	±	3.48
agieval_sat_math	0	acc	36.82	±	3.26
		acc_norm	33.18	±	3.18

Average: 43.5%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	59.47	±	1.43
		acc_norm	61.60	±	1.42
arc_easy	0	acc	85.10	±	0.73
		acc_norm	81.40	±	0.80
boolq	1	acc	87.92	±	0.57
hellaswag	0	acc	66.03	±	0.47
		acc_norm	84.84	±	0.36
openbookqa	0	acc	36.60	±	2.16
		acc_norm	47.40	±	2.24
piqa	0	acc	81.94	±	0.90
		acc_norm	84.28	±	0.85
winogrande	0	acc	76.72	±	1.19

Average: 74.88%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	46.27	±	1.75
		mc2	63.22	±	1.50

Average: 63.22%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	60.00	±	3.56
bigbench_date_understanding	0	multiple_choice_grade	64.50	±	2.49
bigbench_disambiguation_qa	0	multiple_choice_grade	36.82	±	3.01
bigbench_geometric_shapes	0	multiple_choice_grade	23.40	±	2.24
		exact_str_match	1.95	±	0.73
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	32.80	±	2.10
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	24.00	±	1.62
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	54.67	±	2.88
bigbench_movie_recommendation	0	multiple_choice_grade	42.80	±	2.21
bigbench_navigate	0	multiple_choice_grade	52.80	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	68.85	±	1.04
bigbench_ruin_names	0	multiple_choice_grade	51.12	±	2.36
bigbench_salient_translation_error_detection	0	multiple_choice_grade	39.08	±	1.55
bigbench_snarks	0	multiple_choice_grade	76.24	±	3.17
bigbench_sports_understanding	0	multiple_choice_grade	74.85	±	1.38
bigbench_temporal_sequences	0	multiple_choice_grade	58.80	±	1.56
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	21.76	±	1.17
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	17.89	±	0.92
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	54.67	±	2.88

Average: 47.5%

Average score: 57.27% Elapsed time: 02:11:06