Mathematical Reasoning on AIME 25
94.5AccuracyAPRM
Evaluation Results
| Method | Links | |
|---|---|---|
| APRMBackbone=GPT-OSS-120B2025.11 | 94.5 | |
| APRMBackbone=GPT-OSS-20B2025.11 | 93.6 | |
| LLM-JBackbone=GPT-OSS-20B2025.11 | 92.8 | |
| APRMBackbone=Gemma-3-27B2025.11 | 91.9 | |
| LLM-JBackbone=Gemma-3-27B2025.11 | 91.6 | |
| Hard Neg.Backbone=GPT-OSS-120B2025.11 | 91.5 | |
| ReST-MCTSBackbone=GPT-OSS-20B2025.11 | 91.3 | |
| ReST-MCTSBackbone=GPT-OSS-120B2025.11 | 91 | |
| ReST-MCTSBackbone=Gemma-3-27B2025.11 | 90.6 | |
| LLM-JBackbone=GPT-OSS-120B2025.11 | 90.4 | |
| ToTBackbone=GPT-OSS-20B2025.11 | 90.4 | |
| ToTBackbone=GPT-OSS-120B2025.11 | 89.2 | |
| Hard Neg.Backbone=Gemma-3-27B2025.11 | 89.1 | |
| ToTBackbone=Gemma-3-27B2025.11 | 88 | |
| ARMBackbone=GPT-OSS-120B2025.11 | 87.9 | |
| QwenLong-L1.5-30B-A3B2025.12 | 86.46 | |
| CoT-SCBackbone=GPT-OSS-120B2025.11 | 85.5 | |
| Qwen3-30B-A3B-Thinking-25072025.12 | 82.81 | |
| ARMBackbone=Gemma-3-27B2025.11 | 71.4 | |
| CoT-SCBackbone=GPT-OSS-20B2025.11 | 69.9 | |
| CoT-SCBackbone=Gemma-3-27B2025.11 | 69.9 | |
| APRMBackbone=Gemma-3-12B2025.11 | 65.7 | |
| ReST-MCTSBackbone=Gemma-3-12B2025.11 | 62.6 | |
| ToTBackbone=Gemma-3-12B2025.11 | 61.4 | |
| LLM-JBackbone=Gemma-3-12B2025.11 | 55.4 | |
| CoT-SCBackbone=Gemma-3-12B2025.11 | 53 |