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

Discriminative Evaluation on RuDE base

93.1AD

DeepSeek-V3.1

41.41254.83168.2581.669May 12, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
93.184.373.164.678.8
2026.05
86.676.86358.471.2
2026.05
85.872.768.556.570.9
2026.05
85.778.1657275.2
2026.05
83.577.780.157.674.7
2026.05
80.567.157.451.864.2
2026.05
77.762.962.951.463.7
2026.05
75.660.66049.461.4
2026.05
74.965.257.349.961.8
2026.05
74.562.85949.861.5
2026.05
73.466.457.950.162
2026.05
71.357.455.348.258.1
2026.05
69.963.659.95060.9
2026.05
64.453.950.145.753.5
2026.05
5151.441.337.945.4
2026.05
43.440.742.139.541.4