HyperAI

Question Answering On Casehold

Metrics

Macro F1 (10-fold)

Results

Performance results of various models on this benchmark

Comparison Table
Model NameMacro F1 (10-fold)
when-does-pretraining-help-assessing-self61.3
when-does-pretraining-help-assessing-self68.0
when-does-pretraining-help-assessing-self69.5