List your company

Mathematical Reasoning on ASDiv Aug (Acc, #L)

94.02AccuracyLTF
38.723253.079167.43581.7909Jun 15, 2026

Evaluation results

MethodLinks
LTFModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0694.021.24
ReGuLaRModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.06921.28
CoLaRModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0691.125.51
CoconutModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0691.096
iCoTModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0691.030
SoftCoT++Model=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0690.09120.52
Assist-CoTModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0689.48121.51
CoTModel=LLaMA-3.1 Instruct 8B, Finetuning Setting=true2026.0689.23121.93
LTFModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0684.041.21
LTFModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0679.751.2
ReGuLaRModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0679.461.24
ReGuLaRModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0675.591.21
LTFModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0675.111.22
CoLaRModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0673.055.17
ReGuLaRModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0672.191.24
CoLaRModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0669.365.23
CoLaRModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0667.195.19
CoconutModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0666.766
iCoTModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0658.450
CoconutModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0656.856
SoftCoT++Model=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0656.39119.97
CoconutModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0653.186
Assist-CoTModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0652.42120.11
CoTModel=LLaMA-3.2 Instruct 3B, Finetuning Setting=true2026.0651.08121.67
iCoTModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0648.530
SoftCoT++Model=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0648.51119.93
Assist-CoTModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0646.48119.81
iCoTModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0646.360
SoftCoT++Model=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0645.72119.48
CoTModel=DeepSeek-R1-Distill-Qwen-1.5B, Finetuning Setting=true2026.0645.7120.7
CODIModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0643.936
Assist-CoTModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0642.18119.53
CoTModel=LLaMA-3.2 Instruct 1B, Finetuning Setting=true2026.0640.85120.73