| Benchmark | Model | Rank | Results |
|---|---|---|---|
| arithmetic-reasoning-on-gsm8k | Ouro (2.6B) LoopRPT | – | Accuracy: 85.36 |
| code-generation-on-humaneval | Ouro (2.6B) LoopRPT | – | Pass@1: 76.83 |
| code-generation-on-mbpp | Ouro (2.6B) LoopRPT | – | Accuracy: 77.24 |
| common-sense-reasoning-on-winogrande | Ouro (2.6B) LoopRPT | – | Accuracy: 76.47 |
| multi-task-language-understanding-on-mmlu-pro | Ouro (2.6B) LoopRPT | – | Accuracy: 54.19 |
| sentence-completion-on-hellaswag | Ouro (2.6B) LoopRPT | – | Accuracy: 80.03 |