Reading Comprehension on AdversarialQA

Metric: Overall: F1 (higher is better)

LeaderboardDataset
Loading chart...
#ModelOverall: F1Extra DataPaperDateCode
1RoBERTa-Large64.4YesBeat the AI: Investigating Adversarial Human Ann...2020-02-02Code
2BERT-Large62.7YesBeat the AI: Investigating Adversarial Human Ann...2020-02-02Code
3BiDAF28.5YesBidirectional Attention Flow for Machine Compreh...2016-11-05Code