| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-lambada | MDN (1.3B) | #74 | Perplexity: 14.87 |
| question-answering-on-boolq | MDN (1.3B) | #105 | Accuracy: 59.63 |
| question-answering-on-piqa | MDN (1.3B) | #147 | Accuracy: 71.87 |
| sentence-completion-on-hellaswag | MDN (1.3B) | #169 | Accuracy: 53.5 |