Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sycophancy Resistance on Anthropic model-written-evals sycophancy suite
Loading...
94.6
Overall Sycophancy Resistance Score
Instruction Tuned
90.544
91.597
92.65
93.703
Jun 4, 2026
Overall Sycophancy Resistance Score
Political Sycophancy Resistance Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Sycophancy Resistance Score
Political Sycophancy Resistance Score
Instruction Tuned
2026.06
94.6
87.4
BCT
2026.06
94.3
87.7
Attention Consistency Training (AttCT)
2026.06
94.2
85.6
ACT
2026.06
94.1
85.3
MLP Consistency Training (MLPCT)
2026.06
93.8
84.4
Baseline
2026.06
90.7
76
Feedback
Search any
task
Search any
task