| mathematical-reasoning-on-amc23 | CriticOPD (Olmo-3-7B-Instruct-SFT) | #3 | Acc: 74.7 |
| mathematical-reasoning-on-olympiadbench | CriticOPD (Olmo-3-7B-Instruct-SFT) | #18 | Accuracy: 62.33 |
| mathematical-reasoning-on-minerva-math | CriticOPD (Qwen3-1.7B-Non-Thinking) | #29 | Accuracy: 37.44 |
| mathematical-reasoning-on-math-500 | CriticOPD (Olmo-3-7B-Instruct-SFT) | #60 | Accuracy: 89.08 |
| mathematical-reasoning-on-aime24 | CriticOPD (Olmo-3-7B-Instruct-SFT) | #90 | Acc: 43.44 |
| mathematical-reasoning-on-aime-2025 | CriticOPD (Olmo-3-7B-Instruct-SFT) | #101 | Accuracy: 37.81 |