| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | EvoHeir (Gemma-4-E4B-it) | – | Accuracy: 37.15 |
| mathematical-reasoning-on-aime-2026 | EvoHeir (Gemma-4-E4B-it) | – | Accuracy: 41.88 |
| mathematical-reasoning-on-math-500 | EvoHeir (Gemma-4-E4B-it) | – | Accuracy: 86.87 |
| mathematical-reasoning-on-minerva-math | EvoHeir (Qwen3-8B-Base) | – | Accuracy: 45.22 |
| mathematical-reasoning-on-olympiadbench | EvoHeir (Gemma-4-E4B-it) | – | Accuracy: 64.14 |