| common-sense-reasoning-on-arc-easy | LLaMA 13B + CFG (0-shot) | – | Accuracy: 79.1 |
| common-sense-reasoning-on-arc-easy | LLaMA 30B + CFG (0-shot) | – | Accuracy: 83.2 |
| common-sense-reasoning-on-arc-easy | LLaMA 65B + CFG (0-shot) | – | Accuracy: 84.2 |
| common-sense-reasoning-on-arc-easy | LLaMA 7B + CFG (0-shot) | – | Accuracy: 58.9 |
| language-modelling-on-lambada | LLaMA-13B+CFG (zero-shot) | – | Accuracy: 82.2 |
| language-modelling-on-lambada | LLaMA-30B+CFG (zero-shot) | – | Accuracy: 83.9 |
| language-modelling-on-lambada | LLaMA-65B+CFG (Zero-Shot) | – | Accuracy: 84.0 |
| sentence-completion-on-hellaswag | LLaMA 13B + CFG (0-shot) | – | Accuracy: 82.1 |
| sentence-completion-on-hellaswag | LLaMA 30B + CFG (0-shot) | – | Accuracy: 85.3 |
| sentence-completion-on-hellaswag | LLaMA 65B + CFG (0-shot) | – | Accuracy: 86.3 |