Question Answering On Stepgame
Metriken
1-of-100 Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | 1-of-100 Accuracy | Paper Title | Repository |
---|---|---|---|
TP-MANN | 52.99 | StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts |
0 of 1 row(s) selected.