List your company

Question Answering on TabMWP (EM/F1)

37.8EMAdaCAD
0.0489.84919.6529.451Jun 9, 2026

Evaluation results

MethodLinks
AdaCADModel=Qwen2.5-7B2026.0637.840.27
GreedyModel=Qwen2.5-7B2026.0637.539.68
ARRModel=Qwen2.5-7B2026.063739.54
COIECDModel=Qwen2.5-7B2026.0636.539.63
GreedyModel=Mistral-7B-Inst2026.0634.539.21
AdaCADModel=Mistral-7B-Inst2026.0633.938.29
COIECDModel=Mistral-7B-Inst2026.0631.535.8
CoCoAModel=Mistral-7B-Inst2026.0630.434.63
ARRModel=Mistral-7B-Inst2026.0630.436.59
ARRModel=Llama3-8B2026.063035.16
CoCoAModel=Qwen2.5-7B2026.0629.933.18
AdaCADModel=Llama3-8B2026.0629.735.34
GreedyModel=Llama3-8B2026.0629.535.31
CoCoAModel=Llama3-8B2026.0625.130.66
CADModel=Mistral-7B-Inst2026.0621.928.27
AdaCADModel=Llama2-13B2026.0621.724.51
ARRModel=Llama2-13B2026.0621.222.88
GreedyModel=Llama2-13B2026.0621.123.41
COIECDModel=Llama3-8B2026.0619.123.04
COIECDModel=Llama2-13B2026.0618.722.12
CoCoAModel=Llama2-13B2026.0618.521.55
ARRModel=Llama3-8B-Inst2026.0616.721.39
CADModel=Llama2-13B2026.0614.817.82
GreedyModel=Llama3-8B-Inst2026.0614.219.25
CADModel=Qwen2.5-7B2026.0613.615.71
CADModel=Llama3-8B2026.0612.616.4
AdaCADModel=Llama3-8B-Inst2026.0610.616.24
COIECDModel=Mistral-7B2026.0610.212.3
ARRModel=Llama2-13B-Inst2026.068.214.58
GreedyModel=Mistral-7B2026.067.911.18
CoCoAModel=Qwen2.5-7B-Inst2026.067.511.19
GreedyModel=Llama2-13B-Inst2026.066.813.87
AdaCADModel=Llama2-13B-Inst2026.066.512.53
CoCoAModel=Mistral-7B2026.066.28.21
CoCoAModel=Llama3-8B-Inst2026.066.211.35
ARRModel=Mistral-7B2026.066.110.05
AdaCADModel=Qwen2.5-7B-Inst2026.065.99.26
COIECDModel=Qwen2.5-7B-Inst2026.065.89.16
CADModel=Mistral-7B2026.065.77.46
COIECDModel=Llama3-8B-Inst2026.064.811.08
CADModel=Qwen2.5-7B-Inst2026.063.88.21
AdaCADModel=Mistral-7B2026.063.76.4
COIECDModel=Llama2-13B-Inst2026.063.69.53
CADModel=Llama3-8B-Inst2026.063.47.39
CoCoAModel=Llama2-13B-Inst2026.0638.16
CADModel=Llama2-13B-Inst2026.062.27.86
ARRModel=Qwen2.5-7B-Inst2026.062.14.24
GreedyModel=Qwen2.5-7B-Inst2026.061.54.43