| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-lambada | OA-EM (Llama 3.2 3B) | #28 | Accuracy: 68.5Perplexity: 4.64 |
| question-answering-on-piqa | OA-EM (Llama 3.2 3B) | #104 | Accuracy: 76.2 |
| sentence-completion-on-hellaswag | OA-EM (Llama 3.2 3B) | #108 | Accuracy: 70.4 |