mlabonne

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
zephyr-7b-alpha	38	72.24	56.06	40.57	51.72

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	20.47	±	2.54
		acc_norm	19.69	±	2.50
agieval_logiqa_en	0	acc	31.49	±	1.82