Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
AI Assistance Prevention on DOPE Exam Dataset
Loading...
1
Success Rate
gpt-5.1
0.61728
0.71664
0.816
0.91536
Jan 18, 2026
Success Rate
Success Rate 95% CI
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Success Rate 95% CI
gpt-5.1
Best Method=ICW + Font...
2026.01
1
-
gpt-4o
Best Method=ICW + Font...
2026.01
0.981
-
DOPE (Average best hybrid)
Description=Average of...
2026.01
0.963
-
sonnet 4.5
Best Method=ICW + Font...
2026.01
0.936
-
opus 4.5
Best Method=ICW + Font...
2026.01
0.936
-
ICW baseline (Average)
Description=Average pr...
2026.01
0.632
-
Feedback
Search any
task
Search any
task