mlabonne

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

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
dolphin-2.8-mistral-7b-v02	38.99	72.22	51.96	40.41	50.9

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	21.65	±	2.59
		acc_norm	20.47	±	2.54
agieval_logiqa_en	0	acc	35.79	±	1.88

mlabonne

Model	EQ-Bench	Average
AlphaMonarch-7B	73.62	73.62

EQ-Bench

Task	Version	Metric	Value		Stderr
eq_bench	2.1	eqbench,none	73.62
		eqbench_stderr,none	2
		percent_parseable,none	97.66

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Hermes-2-Pro-Mistral-7B	44.54	71.2	59.12	41.9	54.19

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	23.23	±	2.65
		acc_norm	22.83	±	2.64
agieval_logiqa_en	0	acc	38.40	±	1.91

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
CodeNinja-1.0-OpenChat-7B	39.98	71.77	48.73	40.92	50.35

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	27.17	±	2.80
		acc_norm	26.38	±	2.77
agieval_logiqa_en	0	acc	38.10	±	1.90

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Kunoichi-DPO-v2-7B	44.79	75.05	65.68	47.65	58.29

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	26.38	±	2.77
		acc_norm	24.02	±	2.69
agieval_logiqa_en	0	acc	38.71	±	1.91

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Beyonder-4x7B-v3	45.85	76.67	74.98	50.12	61.91

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	26.38	±	2.77
		acc_norm	24.02	±	2.69
agieval_logiqa_en	0	acc	39.48	±	1.92

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
UltraMerge-7B	44.36	77.15	78.47	49.35	62.33

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	27.56	±	2.81
		acc_norm	23.23	±	2.65
agieval_logiqa_en	0	acc	39.48	±	1.92

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
FrankenMonarch-7B	45.1	75.53	73.86	46.79	60.32

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	25.59	±	2.74
		acc_norm	25.98	±	2.76
agieval_logiqa_en	0	acc	39.02	±	1.91

mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
AlphaMonarch-dora	45.42	76.93	78.48	50.18	62.75

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	28.35	±	2.83
		acc_norm	26.38	±	2.77
agieval_logiqa_en	0	acc	38.71	±	1.91