HyperAI超神经

Logical Reasoning On Ruworldtree

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-language38.0
tape-assessing-few-shot-russian-language83.7
tape-assessing-few-shot-russian-language34.0
tape-assessing-few-shot-russian-language40.7