| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-question-answering-on-openbookqa | Mamba-2-2.7B | #17 | Accuracy: 38.8 |
| language-modelling-on-lambada | Mamba-2-2.7B | #24 | Accuracy: 69.7Perplexity: 4.10 |
| common-sense-reasoning-on-arc-easy | Mamba-2-2.7B | #59 | Accuracy: 69.6 |
| question-answering-on-piqa | Mamba-2-2.7B | #94 | Accuracy: 76.4 |
| common-sense-reasoning-on-winogrande | Mamba-2-2.7B | #98 | Accuracy: 64.0 |
| sentence-completion-on-hellaswag | Mamba-2-2.7B | #126 | Accuracy: 66.6 |