| Benchmark | Model | Rank | Results |
|---|---|---|---|
| mathematical-reasoning-on-aime-2025 | CoTranslator (Qwen3-4B-Thinking-2507) | – | Accuracy: 45.36 |
| mathematical-reasoning-on-aime-2026 | CoTranslator (Qwen3-4B-Thinking-2507) | – | Accuracy: 46.51 |
| mathematical-reasoning-on-omni-math | CoTranslator (Qwen3-4B-Thinking-2507) | – | Accuracy: 50.99 |