List your company

Mathematical Reasoning on SVAMP (Acc, Cost)

79.53AccuracyCoT
-2.234818.992640.2261.4474Mar 14, 2026

Evaluation results

MethodLinks
CoTModel=Gemma32026.0379.532,504
CoTModel=Llama3.12026.0376.212,257
CoTModel=Qwen3-8B2026.0375.762,125
DSTModel=Llama3.12026.031.9902
DSTModel=Gemma32026.031.81,111
ToTModel=Llama3.12026.031.694,294
ToTModel=Gemma32026.031.644,702
DSTModel=Qwen3-8B2026.031.482,365
ToTModel=Qwen3-8B2026.031.353,903
DPTSModel=Llama3.12026.030.983,049
DPTSModel=Qwen3-8B2026.030.922,855
DPTSModel=Gemma32026.030.913,597