| Benchmark | Model | Rank | Results |
|---|---|---|---|
| natural-language-inference-on-multinli | Snorkel MeTaL (ensemble) | #16 | Matched: 87.6Mismatched: 87.2 |
| paraphrase-identification-on-quora-question-pairs | Snorkel MeTaL(ensemble) | #8 | F1: 73.1Accuracy: 89.9 |
| sentiment-analysis-on-sst-2-binary-classification | Snorkel MeTaL(ensemble) | #18 | Accuracy: 96.2 |