Mathematical Reasoning on MATH 500 (p@1, p@16)
98.35P@1ST-G
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ST-GModel=Qwen3-30B-A3B-Thinking2026.02 | 98.35 | 99.6 | |
| DoLaModel=Qwen3-30B-A3B-Thinking2026.02 | 98.31 | 99.6 | |
| CoTModel=Qwen3-30B-A3B-Thinking2026.02 | 98.3 | 99.6 | |
| LEDModel=Qwen3-30B-A3B-Thinking2026.02 | 98.3 | 99.6 | |
| STModel=Qwen3-30B-A3B-Thinking2026.02 | 98.25 | 99 | |
| LEDModel=Qwen3-4B-Thinking2026.02 | 97.92 | 99.4 | |
| CoTModel=Qwen3-4B-Thinking2026.02 | 97.86 | 99.2 | |
| DoLaModel=Qwen3-4B-Thinking2026.02 | 97.85 | 99.4 | |
| STModel=Qwen3-4B-Thinking2026.02 | 97.65 | 98.6 | |
| ST-GModel=Qwen3-4B-Thinking2026.02 | 97.62 | 99.2 | |
| ST-GModel=MiMo-7B-RL2026.02 | 95.99 | 99 | |
| CoTModel=MiMo-7B-RL2026.02 | 95.35 | 98.8 | |
| LEDModel=MiMo-7B-RL2026.02 | 95.35 | 99 | |
| DoLaModel=MiMo-7B-RL2026.02 | 95.07 | 98.8 | |
| STModel=MiMo-7B-RL2026.02 | 94.06 | 98.4 |