| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-minerva-math | Qwen3-30B-A3B + AntiSD | #11 | Accuracy: 49.7 |
| mathematical-reasoning-on-hmmt-feb-2025 | Olmo3-7B-TK + AntiSD | #12 | Accuracy: 56.2 |
| mathematical-reasoning-on-aime-2026 | Olmo3-7B-TK + AntiSD | #32 | Accuracy: 76.1 |
| mathematical-reasoning-on-aime24 | Qwen3-30B-A3B + AntiSD | #35 | Acc: 79.4 |
| mathematical-reasoning-on-aime-2025 | Qwen3-30B-A3B + AntiSD | #45 | Accuracy: 75.6 |