List your company

Data Ranking on Mistake math

0.79AUROCVECFILTER
0.18680.34340.50.6566May 20, 2026

Evaluation results

MethodLinks
VECFILTERModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.79
PRISMModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.79
CONCEPTINFModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.73
PRISMModel=Qwen-3-14B, Mix ratio=50%2026.050.72
PRISMModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.71
PRISMModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.7
PRISMModel=Qwen-3-8B, Mix ratio=20%2026.050.7
VECFILTERModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.69
PRISMModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.69
CONCEPTINFModel=Qwen-3-14B, Mix ratio=1%2026.050.69
PRISMModel=Qwen-3-14B, Mix ratio=20%2026.050.69
PRISMModel=Qwen-3-8B, Mix ratio=50%2026.050.68
VECFILTERModel=Qwen-3-14B, Mix ratio=20%2026.050.67
VECFILTERModel=Qwen-3-14B, Mix ratio=50%2026.050.67
PRISMModel=Qwen-3-14B, Mix ratio=10%2026.050.67
VECFILTERModel=Qwen-3-8B, Mix ratio=50%2026.050.66
PRISMModel=Qwen-3-8B, Mix ratio=1%2026.050.66
VECFILTERModel=Qwen-3-14B, Mix ratio=1%2026.050.66
CONCEPTINFModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.65
IF-GUIDEModel=Qwen-3-14B, Mix ratio=50%2026.050.65
IF-GUIDEModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.63
PRISMModel=Qwen-3-8B, Mix ratio=10%2026.050.63
VECFILTERModel=Qwen-3-14B, Mix ratio=10%2026.050.63
IF-GUIDEModel=Qwen-3-14B, Mix ratio=20%2026.050.63
PROJDIFFModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.61
IF-GUIDEModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.61
IF-GUIDEModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.58
PROJDIFFModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.57
VECFILTERModel=Qwen-3-8B, Mix ratio=1%2026.050.56
VECFILTERModel=Qwen-3-8B, Mix ratio=10%2026.050.56
IF-GUIDEModel=Qwen-3-8B, Mix ratio=20%2026.050.56
PROJDIFFModel=Qwen-3-14B, Mix ratio=20%2026.050.56
IF-GUIDEModel=Qwen-3-8B, Mix ratio=10%2026.050.55
IF-GUIDEModel=Qwen-3-8B, Mix ratio=50%2026.050.55
PRISMModel=Qwen-3-14B, Mix ratio=1%2026.050.55
PROJDIFFModel=Qwen-3-14B, Mix ratio=50%2026.050.54
IF-GUIDEModel=Qwen-3-14B, Mix ratio=10%2026.050.54
ICL-EMModel=Qwen-3-14B, Mix ratio=50%2026.050.54
IF-GUIDEModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.53
PROJDIFFModel=Qwen-3-14B, Mix ratio=1%2026.050.53
PROJDIFFModel=Qwen-3-14B, Mix ratio=10%2026.050.53
ICL-EMModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.52
PROJDIFFModel=Qwen-3-8B, Mix ratio=50%2026.050.52
IF-GUIDEModel=Qwen-3-8B, Mix ratio=1%2026.050.52
ICL-EMModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.51
PROJDIFFModel=Qwen-3-8B, Mix ratio=1%2026.050.51
PROJDIFFModel=Qwen-3-8B, Mix ratio=10%2026.050.51
PROJDIFFModel=Qwen-3-8B, Mix ratio=20%2026.050.51
ICL-EMModel=Qwen-3-8B, Mix ratio=50%2026.050.51
IF-GUIDEModel=Qwen-3-14B, Mix ratio=1%2026.050.51
ICL-EMModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.5
ICL-EMModel=Qwen-3-8B, Mix ratio=20%2026.050.5
SAE-FEATModel=Qwen-3-8B, Mix ratio=50%2026.050.49
VECFILTERModel=Qwen-3-8B, Mix ratio=20%2026.050.48
SAE-FEATModel=Qwen-3-8B, Mix ratio=20%2026.050.48
SAE-FEATModel=Qwen-3-8B, Mix ratio=1%2026.050.47
SAE-FEATModel=Qwen-3-8B, Mix ratio=10%2026.050.47
ICL-EMModel=Qwen-3-8B, Mix ratio=10%2026.050.47
ICL-EMModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.46
CONCEPTINFModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.45
CONCEPTINFModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.44
SAE-FEATModel=Llama-3.1-8B-Instruct, Mix ratio=1%2026.050.41
SAE-FEATModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.41
SAE-FEATModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.41
CONCEPTINFModel=Qwen-3-8B, Mix ratio=1%2026.050.41
SAE-FEATModel=Qwen-3-14B, Mix ratio=10%2026.050.41
SAE-FEATModel=Qwen-3-14B, Mix ratio=50%2026.050.41
CONCEPTINFModel=Qwen-3-8B, Mix ratio=10%2026.050.4
CONCEPTINFModel=Qwen-3-14B, Mix ratio=10%2026.050.4
SAE-FEATModel=Qwen-3-14B, Mix ratio=20%2026.050.4
ICL-EMModel=Qwen-3-14B, Mix ratio=20%2026.050.4
SAE-FEATModel=Llama-3.1-8B-Instruct, Mix ratio=10%2026.050.39
SAE-FEATModel=Qwen-3-14B, Mix ratio=1%2026.050.39
CONCEPTINFModel=Qwen-3-8B, Mix ratio=20%2026.050.38
CONCEPTINFModel=Qwen-3-8B, Mix ratio=50%2026.050.37
ICL-EMModel=Qwen-3-8B, Mix ratio=1%2026.050.37
ICL-EMModel=Qwen-3-14B, Mix ratio=10%2026.050.36
PROJDIFFModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.35
PROJDIFFModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.35
ICL-EMModel=Qwen-3-14B, Mix ratio=1%2026.050.31
VECFILTERModel=Llama-3.1-8B-Instruct, Mix ratio=50%2026.050.29
VECFILTERModel=Llama-3.1-8B-Instruct, Mix ratio=20%2026.050.27
CONCEPTINFModel=Qwen-3-14B, Mix ratio=50%2026.050.22
CONCEPTINFModel=Qwen-3-14B, Mix ratio=20%2026.050.21