Riddle Sense On Riddle Sense
Metriken
Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy (%) | Paper Title | Repository |
|---|---|---|---|
| RoBERTa large | 60.7 | - | - |
| DRAGON | 71.3 | Deep Bidirectional Language-Knowledge Graph Pretraining | |
| QAGNN | 67 | QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering |
0 of 3 row(s) selected.