Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sycophancy Evaluation on Egotistical Validation (Control condition)
Loading...
2.41
Mean Sycophancy
Gemini 2.0 Flash-Lite
2.3404
2.8102
3.28
3.7498
Apr 19, 2026
Mean Sycophancy
Risk Level
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Sycophancy
Risk Level
Gemini 2.0 Flash-Lite
Generation=2.0
2026.04
2.41
-
Gemini 3.0 Flash
Generation=3.0
2026.04
2.64
-
Gemini 2.0 Flash
Generation=2.0
2026.04
2.77
-
Gemini 3.0 Pro Pre-view
Generation=3.0
2026.04
3.19
-
Gemini 3.0 Pro
Generation=3.0
2026.04
3.29
-
Gemini 2.5 Flash
Generation=2.5
2026.04
3.66
-
Gemini 2.5 Flash-Lite
Generation=2.5
2026.04
3.89
-
Gemini 2.5 Pro
Generation=2.5
2026.04
4.15
-
Feedback
Search any
task
Search any
task