List your company

Quality Estimation on EN-DE Gender-explicit

99.7AccuracyFairQE (ours, w/ COMETKiwi 22)
93.77295.31196.8598.389Apr 23, 2026

Evaluation results

MethodLinks
FairQE (ours, w/ COMETKiwi 22)Backbone=COMETKiwi 222026.0499.7
COMETKiwi 22Backbone=COMETKiwi, Model Scale=222026.0499.2
COMETKiwi 23 XLBackbone=COMETKiwi, Model Scale=23 XL2026.0498.7
MetricX 24 XLBackbone=MetricX, Model Scale=24 XL2026.0498.5
FairQE (ours, w/ MetricX 24 L)Backbone=MetricX 24 L2026.0498.2
MetricX 24 LBackbone=MetricX, Model Scale=24 L2026.0497.6
GEMBA-MQMBackbone=GEMBA-MQM2026.0494