Mathematical Reasoning on AIME 30 2026 (pass@1, pass@5)
6.17Pass@1 RateDeepSeek-R1-Qwen-1.5B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=162026.06 | 6.17 | 11.78 | |
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=42026.06 | 4.5 | 9.82 | |
| DeepSeek-R1-Qwen-1.5BGroup Size (G)=Base2026.06 | 1.33 | 5.19 | |
| DeepSeek-7BGroup Size (G)=42026.06 | 0.34 | 1.67 | |
| DeepSeek-7BGroup Size (G)=Base2026.06 | 0 | 0 | |
| DeepSeek-7BGroup Size (G)=162026.06 | 0 | 0 | |
| Nemotron-4BGroup Size (G)=Base2026.06 | 0 | 0 | |
| Nemotron-4BGroup Size (G)=162026.06 | 0 | 0 | |
| Nemotron-4BGroup Size (G)=42026.06 | 0 | 0 |