HyperAI超神经

Scienceqa

评估指标

avg
g1-6
g7-12
img
lan
llm_model
model_url
nat
no
organization
parameters
release_date
soc
txt
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avgg1-6g7-12imglanllm_modelmodel_urlnatnoorganizationparametersrelease_datesoctxtupdated_time
模型 196.1896.4495.7294.795.55Mutimodal-T-SciQ_Largehttps://github.com/T-SciQ/T-SciQ96.8996.79Singapore Management University738M2023/5/595.1696.532022.11.28