| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-question-answering-on-openbookqa | MoLM-8B-K2 (0-shot) | #25 | Accuracy: 23.8 |
| common-sense-reasoning-on-arc-easy | MoLM-8B-K2 (0-shot) | #75 | Accuracy: 62.46 |
| question-answering-on-piqa | MoLM-8B-K2 (0-shot) | #126 | Accuracy: 72.91 |
| code-generation-on-humaneval | MoLM-8B-K2 | #139 | Pass@1: 5.51 |
| sentence-completion-on-hellaswag | MoLM-8B-K2 (0-shot) | #193 | Accuracy: 43.33 |