Mathematical Reasoning On Pgps9K
评估指标
Completion accuracy
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Completion accuracy | Paper Title | Repository |
---|---|---|---|
PGPSNet | 62.7 | A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram | - |
NGS | 34.1 | GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning | - |
Inter-GPS | 59.8 | Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning | - |
Geoformer | 35.6 | UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression | - |
GAPS | 61.2 | GAPS: Geometry-Aware Problem Solver | - |
GOLD | 65.8 | GOLD: Geometry Problem Solver with Natural Language Description | - |
0 of 6 row(s) selected.