Mathematical Reasoning on OpenMath2 2000
62.15Pass@1DeepSeek-R1-Qwen-1.5B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=162026.06 | 62.15 | 79.58 | |
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=42026.06 | 59.05 | 77.88 | |
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=Base2026.06 | 54.42 | 75.95 | |
| DeepSeek-7BGroup Size (G)=162026.06 | 29.26 | 49.65 | |
| DeepSeek-7BGroup Size (G)=42026.06 | 27.84 | 48.35 | |
| DeepSeek-7BGroup Size (G)=Base2026.06 | 26.88 | 49.15 | |
| Nemotron-4BGroup Size (G)=162026.06 | 24.52 | 44.35 | |
| Nemotron-4BGroup Size (G)=42026.06 | 22.51 | 42.73 | |
| Nemotron-4BGroup Size (G)=Base2026.06 | 20.91 | 42 |