| Benchmark | Model | Rank | Results |
|---|---|---|---|
| common-sense-reasoning-on-winogrande | FactorEngram (1B) | – | Accuracy: 58.48 |
| language-modelling-on-lambada | FactorEngram (1B) | – | Perplexity: 11.39 |
| question-answering-on-boolq | FactorEngram (1B) | – | Accuracy: 60.88 |
| question-answering-on-piqa | FactorEngram (1B) | – | Accuracy: 72.46 |
| sentence-completion-on-hellaswag | FactorEngram (1B) | – | Accuracy: 57.02 |