| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-piqa | BLT-Space 8B | #50 | Accuracy: 81.1 |
| multi-task-language-understanding-on-mmlu | BLT-Entropy 8B (5-shot) | #56 | Average (%): 57.4 |
| sentence-completion-on-hellaswag | BLT-Entropy 8B | #71 | Accuracy: 80.6 |
| code-generation-on-humaneval | BLT-Entropy 8B | #116 | Pass@1: 35.4 |
| code-generation-on-mbpp | BLT-Entropy 8B (3-shot) | #132 | Accuracy: 41.8 |