Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Sycophancy Evaluation Opinion

8.14PSS

Mistral-7B

1.94163.55085.166.7692Apr 7, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
8.146.1418.729.63
2026.04
6.817.2421.037.12
2026.04
6.517.0322.147.74
2026.04
6.287.1221.438.41
2026.04
5.318.4723.7116.14
2026.04
4.879.1827.414.18
2026.04
4.1210.4131.243.41
2026.04
4.039.3427.1820.87
2026.04
3.9110.4730.123.14
2026.04
3.4710.3829.4118.12
2026.04
3.1411.8332.477.14
2026.04
3.1218.2142.140
2026.04
2.4712.7135.148.31
2026.04
2.1813.8436.189.14