HyperAI超神经

Logical Reasoning On Winograd Automatic

评估指标

Accuracy

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Accuracy
tape-assessing-few-shot-russian-language57.9
tape-assessing-few-shot-russian-language57.2
tape-assessing-few-shot-russian-language87.0
tape-assessing-few-shot-russian-language55.5