ResearchBenchmarksMultiple Change-point Detection on Story dataset Claude 4.5 K=3Follow0.31WD ScoreVCP0.23480.74241.251.7576May 5, 2026Evaluation ResultsMethodMethodLinksWD ScoreCE ScoreVCPGenerator=Claude 4.5Generator=Claude 4.52026.050.31-2.9WCPGenerator=Claude 4.5Generator=Claude 4.52026.050.31-1.13VotingGenerator=Claude 4.5Generator=Claude 4.52026.050.46-2.78TextTilingGenerator=Claude 4.5Generator=Claude 4.52026.050.72-4.47LLMPredGenerator=Claude 4.5Generator=Claude 4.52026.051.05-4.43SenPredGenerator=Claude 4.5Generator=Claude 4.52026.052.19-17.91