Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prevention on LongForm
Loading...
100
Score (gpt-5.1)
DOPE-v2
70.984
78.517
86.05
93.583
Jan 18, 2026
Score (gpt-5.1)
Score (gpt-4o)
Score (sonnet)
Score (opus)
Updated 4d ago
Evaluation Results
Method
Method
Links
Score (gpt-5.1)
Score (gpt-4o)
Score (sonnet)
Score (opus)
DOPE-v2
configuration=ICW + Fo...
2026.01
100
100
86
86
DOPE-v1
configuration=ICW + Du...
2026.01
97.6
88
88
88
code-glyph
2026.01
87.5
85.8
78
78
TRAPDOC
2026.01
83
81.8
76
76
ICW
2026.01
72.1
64.8
68
68
Feedback
Search any
task
Search any
task