| Benchmark | Model | Rank | Results |
|---|---|---|---|
| common-sense-reasoning-on-winogrande | CoWA (32B) | – | Accuracy: 81.72 |
| multi-task-language-understanding-on-mmlu-pro | CoWA (32B) | – | Accuracy: 68.51 |
| question-answering-on-piqa | CoWA (32B) | – | Accuracy: 85.75 |
| sentence-completion-on-hellaswag | CoWA (32B) | – | Accuracy: 83.1 |