| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-olympiadbench | ThreadWeaver (Qwen3-8B) | #16 | Accuracy: 63.5 |
| mathematical-reasoning-on-minerva-math | ThreadWeaver (Qwen3-8B) | #20 | Accuracy: 43.7 |
| mathematical-reasoning-on-aime24 | ThreadWeaver (Qwen3-8B) | #30 | Acc: 79.9 |
| mathematical-reasoning-on-math-500 | ThreadWeaver (Qwen3-8B) | #53 | Accuracy: 91.4 |
| mathematical-reasoning-on-aime-2025 | ThreadWeaver (Qwen3-8B) | #70 | Accuracy: 60.5 |