| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-question-answering-on-openbookqa | LoopFormer (3x8) | #24 | Accuracy: 26.8 |
| language-modelling-on-lambada | LoopFormer (3x8) | #58 | Accuracy: 38.27 |
| common-sense-reasoning-on-winogrande | LoopFormer (3x4) | #154 | Accuracy: 53.43 |
| question-answering-on-piqa | LoopFormer (3x8) | #165 | Accuracy: 63.33 |
| sentence-completion-on-hellaswag | LoopFormer (3x8) | #214 | Accuracy: 32.3 |