| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-lambada | xLSTM[1:0] 1.3B | #36 | Accuracy: 57.83Perplexity: 6.86 |
| common-sense-reasoning-on-arc-easy | xLSTM[7:1] 1.3B | #74 | Accuracy: 65.11 |
| common-sense-reasoning-on-winogrande | xLSTM[1:0] 1.3B | #113 | Accuracy: 60.62 |
| question-answering-on-piqa | xLSTM[7:1] 1.3B | #115 | Accuracy: 74.92 |
| sentence-completion-on-hellaswag | xLSTM[1:0] 1.3B | #145 | Accuracy: 60.91 |