Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Quality Estimation on EN-HI Gender-explicit
Loading...
79.1
Accuracy
FairQE (ours, w/ MetricX 24 L)
54.348
60.774
67.2
73.626
Apr 23, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
FairQE (ours, w/ MetricX 24 L)
Backbone=MetricX 24 L
2026.04
79.1
MetricX 24 XL
Backbone=MetricX, Mode...
2026.04
78.9
MetricX 24 L
Backbone=MetricX, Mode...
2026.04
74
FairQE (ours, w/ COMETKiwi 22)
Backbone=COMETKiwi 22
2026.04
74
COMETKiwi 23 XL
Backbone=COMETKiwi, Mo...
2026.04
73.1
GEMBA-MQM
Backbone=GEMBA-MQM
2026.04
72
COMETKiwi 22
Backbone=COMETKiwi, Mo...
2026.04
55.3
Feedback
Search any
task
Search any
task