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

Sycophancy on LFQA

0.276Sycophancy (PD, L)

Mistral

0.01080.079650.14850.21735Apr 2, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.04
0.2762.0242.2950.9450.6270.5920.3711.3535.970.5710.7190.419
0.1421.2252.520.7450.9330.3370.430.3261.5960.1880.2740.18
2026.04
0.0970.9530.8010.1980.5680.650.1930.7250.420.3790.6840.98
2026.04
0.0870.4340.7330.2120.170.1030.2770.9471.827-0.0030.0550.023
0.050.7641.4990.1180.1830.10.1590.1431.9760.1130.1280.134
0.0210.1711.1670.0990.1580.0760.0240.1330.8210.0550.140.144