Mathematical Reasoning on AMC 23 (Acc@16)
70.2Acc@16Qwen2.5-7B + DAPO
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-7B + DAPOModel Family=Qwen Family, Strategy=DAPO2026.01 | 70.2 | |
| Qwen2.5-7B + DAPO-SilhouetteModel Family=Qwen Family, Strategy=DAPO-Silhouette2026.01 | 70.2 | |
| OctoThinker-8B + DAPO-SilhouetteModel Family=OctoThinker Family, Strategy=DAPO-Silhouette2026.01 | 47.2 | |
| OctoThinker-8B + DAPOModel Family=OctoThinker Family, Strategy=DAPO2026.01 | 46.9 | |
| Qwen2.5-7BModel Family=Qwen Family2026.01 | 30.5 | |
| Llama-3.1-8B-Instruct + DAPO-SilhouetteModel Family=Llama Family, Strategy=DAPO-Silhouette2026.01 | 27.7 | |
| Llama-3.1-8B-Instruct + DAPOModel Family=Llama Family, Strategy=DAPO2026.01 | 25.2 | |
| Llama-3.1-8B-InstructModel Family=Llama Family2026.01 | 24.7 | |
| OctoThinker-8BModel Family=OctoThinker Family2026.01 | 18 |