Skip to content

Benchmark

Sycophancy (Lech Mazur)

Scores are percentages. Lower is better.

Models measured
23
Scores recorded
23
Sources
1
IQ weight
1.83

Score distribution

4.8%
Mean
3%
Median
5.7%
Std dev
0.5%
10th percentile
12.6%
90th percentile
0%
Min
0%22.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.83 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard