| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-minerva-math | Qwen3.5-35B w/SAGE | #8 | Accuracy: 51.34 |
| math-word-problem-solving-on-math | Qwen3.5-35B w/SAGE | #10 | Accuracy: 84.72 |
| mathematical-reasoning-on-olympiadbench | Qwen3.5-35B w/SAGE | #10 | Accuracy: 68.26 |
| arithmetic-reasoning-on-gsm8k | Qwen3.5-35B w/SAGE | #32 | Accuracy: 94.16 |
| mathematical-reasoning-on-aime24 | Qwen3.5-35B w/SAGE | #64 | Acc: 62.04 |