HyperAI超神经

Uhgeval

评估指标

doc
gen
kno
llm_model
model_url
num
organization
parameters
release_date
updated_time

评测结果

各个模型在此基准测试上的表现结果

比较表格
模型名称docgenknollm_modelmodel_urlnumorganizationparametersrelease_dateupdated_time
模型 154.97%53.74%59.55%Aquila-34Bhttps://www.researchgate.net/figure/Performance-of-Aquila-34B-a-and-Aquila-70B-expr-b-on-downstream-tasks-during_fig3_38311989053.52%Zhiyuan34BN/A2024.5.24