| Benchmark | Model | Rank | Results |
|---|---|---|---|
| multi-task-language-understanding-on-mmlu-pro | Qwen3-4B-base + SCALER | #74 | Accuracy: 70.0 |
| mathematical-reasoning-on-math-500 | Qwen3-4B-base + SCALER | #76 | Accuracy: 84.4 |
| mathematical-reasoning-on-aime24 | Qwen3-4B-base + SCALER | #102 | Acc: 27.29 |