Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Structural Consistency on Consistency Evaluation Dataset (N=720) (test)

1Structural Consistency Score

Claude-3.7-Sonnet

0.644320.736660.8290.92134Nov 27, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.11
1
2025.11
1
2025.11
1
2025.11
1
2025.11
1
2025.11
1
2025.11
1
2025.11
1
2025.11
0.988
2025.11
0.975
2025.11
0.963
2025.11
0.963
2025.11
0.95
2025.11
0.95
2025.11
0.95
2025.11
0.95
2025.11
0.938
2025.11
0.875
2025.11
0.869
2025.11
0.863
2025.11
0.86
2025.11
0.85
2025.11
0.838
2025.11
0.838
2025.11
0.825
2025.11
0.825
2025.11
0.825
2025.11
0.8
2025.11
0.8
2025.11
0.787
2025.11
0.781
2025.11
0.776
2025.11
0.775
2025.11
0.771
2025.11
0.768
2025.11
0.767
2025.11
0.758
2025.11
0.757
2025.11
0.755
2025.11
0.75
2025.11
0.749
2025.11
0.748
2025.11
0.739
2025.11
0.722
2025.11
0.722
2025.11
0.722
2025.11
0.708
2025.11
0.704
2025.11
0.703
2025.11
0.7
2025.11
0.682
2025.11
0.679
2025.11
0.673
2025.11
0.658