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

Pairwise preference prediction on SpeechEval human preference (test)

86.85Accuracy

PrefSQA-F

79.975681.760383.54585.3297Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
86.85
2026.06
86.31
2026.06
84.32
2026.06
80.24