Common Sense Reasoning on SWAG
Metric: Dev (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | Dev▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | BERT-LARGE | 86.6 | No | BERT: Pre-training of Deep Bidirectional Transfo... | 2018-10-11 | Code |
| 2 | ESIM + ELMo | 59.1 | No | SWAG: A Large-Scale Adversarial Dataset for Grou... | 2018-08-16 | - |
| 3 | ESIM + GloVe | 51.9 | No | SWAG: A Large-Scale Adversarial Dataset for Grou... | 2018-08-16 | - |