Mathematical Reasoning on SVAMP (Acc, Cost)
79.53AccuracyCoT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoTModel=Gemma32026.03 | 79.53 | 2,504 | |
| CoTModel=Llama3.12026.03 | 76.21 | 2,257 | |
| CoTModel=Qwen3-8B2026.03 | 75.76 | 2,125 | |
| DSTModel=Llama3.12026.03 | 1.9 | 902 | |
| DSTModel=Gemma32026.03 | 1.8 | 1,111 | |
| ToTModel=Llama3.12026.03 | 1.69 | 4,294 | |
| ToTModel=Gemma32026.03 | 1.64 | 4,702 | |
| DSTModel=Qwen3-8B2026.03 | 1.48 | 2,365 | |
| ToTModel=Qwen3-8B2026.03 | 1.35 | 3,903 | |
| DPTSModel=Llama3.12026.03 | 0.98 | 3,049 | |
| DPTSModel=Qwen3-8B2026.03 | 0.92 | 2,855 | |
| DPTSModel=Gemma32026.03 | 0.91 | 3,597 |