List your company

Quality Estimation on PAWS-X (test)

0.325BCESigmoid Head
-0.249363.627577.504511.38143Jan 2, 2026

Evaluation results

MethodLinks
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=fr2026.010.325
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=es2026.010.399
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=de2026.010.422
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=zh2026.010.622
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Olmo, Language=en2026.010.883
Sigmoid HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=en2026.011.056
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Tower, Language=fr2026.011.256
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Tower, Language=es2026.011.362
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Tower, Language=de2026.011.645
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=fr2026.011.849
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Tower, Language=en2026.011.925
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=zh2026.012.172
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=es2026.012.309
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Olmo, Language=en2026.012.832
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Tower, Language=zh2026.012.925
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=de2026.013.151
Boosted ProbEvaluation Mode=Eval Self, Backbone Model=Olmo, Language=en2026.013.769
Sigmoid HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=en2026.014.546
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Tower, Language=fr2026.016.297
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Tower, Language=en2026.016.858
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Tower, Language=es2026.017.324
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Tower, Language=de2026.018.726
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=fr2026.018.847
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=de2026.019.025
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Olmo, Language=en2026.019.096
Boosted ProbEvaluation Mode=Eval Others, Backbone Model=Tower, Language=zh2026.019.257
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=es2026.019.334
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=fr2026.019.977
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=en2026.0110.835
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=es2026.0110.868
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=en2026.0111.668
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=de2026.0111.756
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Tower, Language=zh2026.0112.362
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Tower, Language=zh2026.0112.745
Softmax HeadEvaluation Mode=Eval Others, Backbone Model=Olmo, Language=en2026.0113.364
Softmax HeadEvaluation Mode=Eval Self, Backbone Model=Olmo, Language=en2026.0114.684