Mathematical Reasoning on Minerva Math (avg@4)
26.84Avg@4 ScorePion
Evaluation results
| Method | Links | |
|---|---|---|
| PionBase Model=Qwen3-1.7B2026.05 | 26.84 | |
| AdamWBase Model=Qwen3-1.7B2026.05 | 25.91 | |
| MuonBase Model=Qwen3-1.7B2026.05 | 24.08 | |
| PionBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 23.9 | |
| AdamWBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 23.16 | |
| MuonBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 22.89 | |
| BaseBase Model=DeepSeek-R1-Distill-Qwen-1.5B2026.05 | 19.39 | |
| BaseBase Model=Qwen3-1.7B2026.05 | 16.27 |