Mathematical Reasoning On Pgps9K
Metriken
Completion accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
Modellname | Completion accuracy |
---|---|
a-multi-modal-neural-geometric-solver-with | 62.7 |
geoqa-a-geometric-question-answering | 34.1 |
inter-gps-interpretable-geometry-problem | 59.8 |
unigeo-unifying-geometry-logical-reasoning | 35.6 |
gaps-geometry-aware-problem-solver | 61.2 |
gold-geometry-problem-solver-with-natural | 65.8 |