| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-question-answering-on-sciq | SPS XL (LM Evaluation Harness) | #6 | Accuracy: 87.5 |
| language-modelling-on-lambada | SPS XL | #48 | Accuracy: 49.5 |
| common-sense-reasoning-on-arc-easy | SPS XL | #72 | Accuracy: 66.3 |
| question-answering-on-piqa | SPS XL | #146 | Accuracy: 71.9 |
| sentence-completion-on-hellaswag | SPS XL | #163 | Accuracy: 56.3 |