Mathematical Reasoning on AIME 2024 (Avg@16 Accuracy)
60.9Avg@16 AccuracyResRL
Evaluation results
| Method | Links | |
|---|---|---|
| ResRLBase Model=Qwen3-32B, Mode=Think mode, Max response length=81922026.05 | 60.9 | |
| NSR (Weighted-Reinforce)Base Model=Qwen3-32B, Mode=Think mode, Max response length=81922026.05 | 54.7 |