Mathematical Reasoning on MATH 500 (Acc, TR)
94.8AccuracyDynasor
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DynasorModel=Qwen3-30B-A3B-Thinking2026.05 | 94.8 | -4.3 | |
| DEERModel=Qwen3-30B-A3B-Thinking2026.05 | 94.8 | 34.9 | |
| Full CoTModel=Qwen3-30B-A3B-Thinking2026.05 | 94.4 | 0 | |
| PUMAModel=Qwen3-30B-A3B-Thinking2026.05 | 94.2 | 28.8 | |
| Full CoTModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 93.6 | 0 | |
| PUMAModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 92.6 | 15.7 | |
| DEERModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 91.8 | 22.7 | |
| No-ThinkModel=Qwen3-30B-A3B-Thinking2026.05 | 91.8 | 51.7 | |
| Plan&BudgetModel=Qwen3-30B-A3B-Thinking2026.05 | 91.8 | 51.4 | |
| DynasorModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 91.4 | -9 | |
| DEERModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 90.6 | 39.6 | |
| Full CoTModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 90 | 0 | |
| PUMAModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 89.6 | 38.6 | |
| CCoTModel=Qwen3-30B-A3B-Thinking2026.05 | 89.2 | 54.6 | |
| Plan&BudgetModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 89 | 8.3 | |
| CCoTModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 86.6 | 34.5 | |
| CCoTModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 85 | 60.9 | |
| Plan&BudgetModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 84.6 | 48.5 | |
| DynasorModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 84.2 | 30.6 | |
| CoDModel=Qwen3-30B-A3B-Thinking2026.05 | 82.8 | 29.9 | |
| CoDModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 80.4 | 59.9 | |
| No-ThinkModel=DeepSeek-R1-Distill-Qwen-7B2026.05 | 79 | 80 | |
| CoDModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 79 | 30.1 | |
| No-ThinkModel=Llama-3.1-Nemotron-Nano-8B2026.05 | 62.8 | -125.5 | |
| Ans. Conv.Model=DeepSeek-R1-Distill-Qwen-7B2026.05 | 61.8 | 76.5 | |
| Ans. Conv.Model=Qwen3-30B-A3B-Thinking2026.05 | 57 | 87.8 | |
| Ans. Conv.Model=Llama-3.1-Nemotron-Nano-8B2026.05 | 55.8 | 76.3 |