Mathematical Reasoning on AIMO 2025 (reference set)
20Pass@1RHO-LOSS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RHO-LOSSBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Fine-tuning=true, Training Samples=4K2024.06 | 20 | 30 | |
| ScaleBiOBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Fine-tuning=true, Training Samples=4K2024.06 | 20 | 30 | |
| UniformBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Fine-tuning=true, Training Samples=4K2024.06 | 10 | 30 | |
| LESSBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Fine-tuning=true, Training Samples=4K2024.06 | 10 | 30 |