Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sycophancy Evaluation on Early A/B tests Online prevalence
Loading...
-0.69
Prevalence Change (Free Users)
gpt-5-main
-0.7245
-0.70725
-0.69
-0.67275
Dec 19, 2025
Prevalence Change (Free Users)
Prevalence Change (Paid Users)
Updated 4d ago
Evaluation Results
Method
Method
Links
Prevalence Change (Free Users)
Prevalence Change (Paid Users)
gpt-5-main
Test Type=Preliminary...
2025.12
-0.69
-0.75
Feedback
Search any
task
Search any
task