AdvGLUE

The Adversarial GLUE Benchmark

Performance of TBD-name (single) on AdvGLUE

Overall Statistics

Performance of TBD-name (single) on each task

The Stanford Sentiment Treebank (SST-2)

Quora Question Pairs (QQP)

MultiNLI (MNLI) matched

MultiNLI (MNLI) mismatched

Question NLI (QNLI)

Recognizing Textual Entailment (RTE)