| natural-language-inference-on-qnli-glue-dev | MVP | #2 | Accuracy: 95.10 |
| paraphrase-identification-on-mrpc-glue-dev | MVP | #2 | F1: 92.07 |
| natural-language-inference-on-multinli-dev | MVP | #7 | Matched: 89.70 |
| semantic-textual-similarity-on-sts-b-glue-dev | MVP | #7 | Pearson/Spearman Correlation: 91.1 |
| linguistic-acceptability-on-cola-glue-dev | MVP | #9 | Matthews Correlation: 59.87 |
| natural-language-understanding-on-glue-dev | MVP | #9 | GLUE (dev): 85.88 |
| natural-language-inference-on-rte-glue-dev | MVP | #10 | Accuracy: 82.87 |
| text-summarization-on-x-sum | MVP+S | #19 | ROUGE-L: 37.50 |
| abstractive-text-summarization-on-cnn-daily-mail | MVP+S | #43 | ROUGE-L: 41.21 |
| sentiment-analysis-on-sst-2-binary-classification | MVP | #86 | Dev Accuracy: 96.43 |