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

Pairwise Judge Comparison on UltraFeedback core250

161Win Count (W)

TEA

135141.75148.5155.25May 11, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
16164.4
2026.05
15963.6
2026.05
15260.8
2026.05
15260.8
2026.05
14859.2
2026.05
14658.4
2026.05
14558
2026.05
14558
2026.05
14457.6
2026.05
14156.4
2026.05
14156.4
2026.05
14156.4
2026.05
13754.8
2026.05
13654.4