Story dataset
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Story dataset GPT-5-mini K=8
0.43WD
6
Story dataset GPT-5-mini K=3
0.43WD
6
Story dataset GPT-5-mini K=2
0.41WD
6
Story dataset K=1 GPT-5-mini
0.39WD Score
6
Story dataset Claude 4.5, K=8
0.33Word Distance (WD)
6
Story dataset Claude 4.5 K=5
0.32WD
6
Story dataset Claude 4.5 K=3
0.31WD Score
6
Story dataset Claude 4.5 K=2
0.29Word Distance (WD)
6
Story dataset Claude 4.5 K=1
0.26WD
6