Mathematical Reasoning on AIME25 (avg@32)
24.38Avg@32Pion
Evaluation Results
| Method | Links | |
|---|---|---|
| PionBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 24.38 | |
| AdamWBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 23.94 | |
| MuonBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 23.33 | |
| PionBase Model=Qwen3-1.7B2026.05 | 21.98 | |
| AdamWBase Model=Qwen3-1.7B2026.05 | 20.94 | |
| BaseBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 20.83 | |
| MuonBase Model=Qwen3-1.7B2026.05 | 19.27 | |
| BaseBase Model=Qwen3-1.7B2026.05 | 10.1 |