Model Eval results

openllm Benchmark results

Model	Details	Average	arc	gsm8k	hellaswag	mmlu	truthfulqa	winogrande
Arithmo-Wizard-2-7B	complete result	65.22	62.88	61.26	83.15	60.61	45.9	77.51
Meta-Llama-3-8B-Instruct	complete result	68.27	62.2	75.59	78.84	65.82	51.71	75.45
Meta-Llama-3-8B	complete result	62.84	57.51	50.87	82.09	65.04	43.93	77.58
Nereus-7B	complete result	63.81	62.54	46.25	83.23	59.6	54.32	76.95
Orpomis-Prime-7B-dare	complete result	67.37	64.68	59.74	85.12	62.21	53.72	78.77
Orpomis-Prime-7B-it	complete result	55.67	61.26	24.34	79.61	51.55	43.68	73.56
Orpomis-Prime-7B	complete result	55.27	60.67	24.41	79.12	52.43	41.02	73.95
PowerBot-8B	complete result	67.62	60.92	69.07	83.24	66.62	45.11	80.74
Proteus-8B	complete result	70.67	63.48	78.77	82.94	64.71	56.71	77.43
Saga-8B	complete result	52.29	51.11	24.18	74.1	50.65	41.19	72.53
aqua-smaug-0.2-8B	complete result	65.52	60.15	59.44	82.65	65.51	47.28	78.06
aqua-smaug-0.3-8B	complete result	69.73	62.37	76.19	83.02	66.0	53.7	77.11
aqua-smaug-hermes-8B	complete result	69.96	61.77	79.61	82.25	64.96	55.11	76.09
llama-airo-3	complete result	66.52	61.01	56.33	82.42	64.79	56.35	78.22
mera-mix-4x7B	complete result	76.59	71.76	72.93	88.92	63.8	77.6	84.53
mistral-orpo-beta-NeuralBeagle14-7B-dare-ties	complete result	70.06	67.32	61.79	85.89		54.17	81.14

nous Benchmark results

Model	Details	Average	agieval	bigbench	gpt4all	truthfulqa
Arithmo-Wizard-2-7B	complete result	46.28	31.58	37.44	70.2	45.91
Nereus-7B	complete result	52.12	42.8	39.17	72.21	54.32
Orpomis-Prime-7B-dare	complete result	52.42	42.71	39.82	73.42	53.72
Orpomis-Prime-7B-it	complete result	47.98	37.23	38.72	72.28	43.68
Orpomis-Prime-7B	complete result	46.78	36.4	37.5	72.18	41.02
bert-tiny-finetuned-sms-spam-detection	complete result	33.97	22.95	28.75	36.07	48.09
llama-airo-3	complete result	51.1	36.59	39.26	72.24	56.3