Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Story dataset

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multiple change-point detectionStory dataset GPT-5-mini K=8
WD0.43
6
Multiple change-point detectionStory dataset GPT-5-mini K=3
WD0.43
6
Multiple change-point detectionStory dataset GPT-5-mini K=2
WD0.41
6
Multiple change-point detectionStory dataset K=1 GPT-5-mini
WD Score0.39
6
Multiple change-point detectionStory dataset Claude 4.5, K=8
Word Distance (WD)0.33
6
Multiple change-point detectionStory dataset Claude 4.5 K=5
WD0.32
6
Multiple change-point detectionStory dataset Claude 4.5 K=3
WD Score0.31
6
Multiple change-point detectionStory dataset Claude 4.5 K=2
Word Distance (WD)0.29
6
Multiple change-point detectionStory dataset Claude 4.5 K=1
WD0.26
6
Showing 9 of 9 rows