| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-lambada | GPT-J 6B | #24 | Accuracy: 69.7Perplexity: 3.99 |
| common-sense-reasoning-on-winogrande | GPT-J 6B | #93 | Accuracy: 65.3 |
| question-answering-on-piqa | GPT-J 6B | #99 | Accuracy: 76.5 |
| sentence-completion-on-hellaswag | GPT-J 6B | #130 | Accuracy: 66.1 |