| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-olympiadbench | SAGE (Qwen3-4B-Instruct) | #6 | Accuracy: 71.2 |
| mathematical-reasoning-on-minerva-math | SAGE (Qwen3-4B-Instruct) | #12 | Accuracy: 49.2 |
| mathematical-reasoning-on-math-500 | SAGE (Qwen3-4B-Instruct) | #23 | Accuracy: 95.4 |
| multi-task-language-understanding-on-mmlu-pro | SAGE (Qwen3-4B-Instruct) | #66 | Accuracy: 72.5 |
| mathematical-reasoning-on-aime-2025 | SAGE (Qwen3-4B-Instruct) | #82 | Accuracy: 52.1 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | SAGE (Qwen3-4B-Instruct) | #99 | Accuracy: 57.8 |