| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-boolq | Mimir 1B | #14 | Accuracy: 87.8 |
| common-sense-reasoning-on-winogrande | Mimir 1B | #63 | Accuracy: 73.5 |
| code-generation-on-humaneval | Mimir 1B | #98 | Pass@1: 56.7 |
| sentence-completion-on-hellaswag | Mimir 1B | #123 | Accuracy: 67.3 |