List your company

Logical Reasoning on MNLogic 3dgt

99.83AccuracyEnd2end FT
49.109262.277175.44588.6129Mar 25, 2026

Evaluation results

MethodLinks
End2end FTBackbone Scale=7B, Random Seeds=52026.0399.83
VLCBackbone Scale=7B, Random Seeds=52026.0397.37
ViperGPTBackbone Scale=7B, Random Seeds=52026.0385.66
End2end RSBackbone Scale=7B, Random Seeds=52026.0371.73
PrismBackbone Scale=7B, Random Seeds=52026.0351.06