List your company

Math Word Problem solving on SVAMP English (test)

67.8AccuracyATHENA
7.37623.06338.7554.437Nov 2, 2023

Evaluation results

MethodLinks
ATHENABackbone=RoBERTa-large2023.1167.8
ATHENABackbone=RoBERTa-large2023.1154.8
ATHENABackbone=RoBERTa-base2023.1152.5
DeductReasonerBackbone=RoBERTa-large2023.1151.6
DeductReasonerBackbone=RoBERTa-large2023.1150.3
ATHENABackbone=RoBERTa-base2023.1145.6
DeductReasonerBackbone=RoBERTa-base2023.1145
R-Graph-to-TreeBackbone=RoBERTa-base2023.1143.8
DeductReasonerBackbone=RoBERTa-base2023.1142.5
R-GTSBackbone=RoBERTa-base2023.1141
R-GTSBackbone=RoBERTa-base2023.1140.9
Graph-to-TreeBackbone=Random embedding2023.1136.5
R-Graph-to-TreeBackbone=RoBERTa-base2023.1131.8
GTSBackbone=Random embedding2023.1130.8
R-TransformerBackbone=RoBERTa-base2023.1130.3
Graph-to-TreeBackbone=Random embedding2023.1125.3
TransformerBackbone=Random embedding2023.1120.7
R-TransformerBackbone=RoBERTa-base2023.1113.5
GTSBackbone=Random embedding2023.1112.2
TransformerBackbone=Random embedding2023.119.7