Command Palette
Search for a command to run...
Mathematical Reasoning On Geoqa
평가 지표
Accuracy (%)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
| Paper Title | ||
|---|---|---|
| GOLD | 75.2 | GOLD: Geometry Problem Solver with Natural Language Description |
| GAPS | 67.8 | GAPS: Geometry-Aware Problem Solver |
0 of 2 row(s) selected.