Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Single change-point detection on Story
Loading...
0.207
WD
WCP
0.10092
0.81696
1.533
2.24904
May 5, 2026
WD
CE
Updated 28d ago
Evaluation Results
Method
Method
Links
WD
CE
WCP
Model=Claude 4.5
2026.05
0.207
0
VCP
Model=Claude 4.5
2026.05
0.272
0
WCP
Model=GPT-5-mini
2026.05
0.321
0
VCP
Model=GPT-5-mini
2026.05
0.356
0
Voting
Model=Claude 4.5
2026.05
0.443
-1.48
TextTiling
Model=Claude 4.5
2026.05
0.805
-2.97
Voting
Model=GPT-5-mini
2026.05
0.925
-3.37
TextTiling
Model=GPT-5-mini
2026.05
0.969
-3.48
LLMPred
Model=GPT-5-mini
2026.05
1.361
-4.02
LLMPred
Model=Claude 4.5
2026.05
1.526
-4.62
SenPred
Model=Claude 4.5
2026.05
2.343
-9.43
SenPred
Model=GPT-5-mini
2026.05
2.859
-11.46
Feedback
Search any
task
Search any
task