RPGBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
RPGBench Aggregate (Overall)
-0.026Avg Score
18
RPGBench Dialogue Shift (Generalization)
-0.956Turn Composition
18
RPGBench Character Shift (Generalization)
-0.8Deviation Score (Literature)
18
RPGBench User Shift Generalization
-0.016RP Score (German)
18
RPGBench In-distribution
-0.034R-EMI
18