| Benchmark | Model | Rank | Results |
|---|---|---|---|
| common-sense-reasoning-on-winogrande | FineRMoE (Qwen2.5-7B) | #54 | Accuracy: 75.69 |
| code-generation-on-mbpp | FineRMoE (Qwen2.5-7B) | #60 | Accuracy: 69.4 |
| sentence-completion-on-hellaswag | FineRMoE (Qwen2.5-7B) | #77 | Accuracy: 79.51 |
| arithmetic-reasoning-on-gsm8k | FineRMoE (Qwen2.5-7B) | #113 | Accuracy: 85.37 |