List your company

Uncertainty Quantification on WMT 19

0.608COMET AUCKLE
0.513360.537930.56250.58707Jan 29, 2026

Evaluation results

MethodLinks
KLEBackbone Model=Gemma-3-4B2026.010.6080.559
Structure-Aware Minimum Bayes Risk DecodingBackbone Model=Gemma-3-4B2026.010.6080.584
SARBackbone Model=Gemma-3-4B2026.010.6060.574
Structure-Aware Minimum Bayes Risk DecodingBackbone Model=Qwen3-4B2026.010.6030.578
KLEBackbone Model=Qwen3-30B-A3B2026.010.5990.537
Structure-Aware Minimum Bayes Risk DecodingBackbone Model=Qwen3-30B-A3B2026.010.5990.57
COCOABackbone Model=Qwen3-30B-A3B2026.010.5970.556
Structure-Aware Minimum Bayes Risk DecodingBackbone Model=Gemma-3-12B2026.010.5960.579
KLEBackbone Model=Qwen3-4B2026.010.5940.539
COCOABackbone Model=Qwen3-4B2026.010.5910.556
KLEBackbone Model=Gemma-3-12B2026.010.590.539
COCOABackbone Model=Gemma-3-4B2026.010.5890.555
SARBackbone Model=Gemma-3-12B2026.010.5870.562
COCOABackbone Model=Gemma-3-12B2026.010.5860.542
SARBackbone Model=Qwen3-30B-A3B2026.010.5830.548
SARBackbone Model=Qwen3-4B2026.010.580.549
MSPBackbone Model=Qwen3-30B-A3B2026.010.5770.547
MSPBackbone Model=Qwen3-4B2026.010.5730.553
MSPBackbone Model=Gemma-3-12B2026.010.5720.532
MSPBackbone Model=Gemma-3-4B2026.010.5630.535
P(True)Backbone Model=Gemma-3-12B2026.010.5570.495
SEBackbone Model=Gemma-3-4B2026.010.5430.531
P(True)Backbone Model=Gemma-3-4B2026.010.5370.485
SEBackbone Model=Qwen3-4B2026.010.5330.517
P(True)Backbone Model=Qwen3-4B2026.010.5230.55
SEBackbone Model=Gemma-3-12B2026.010.5180.513
P(True)Backbone Model=Qwen3-30B-A3B2026.010.5170.506
SEBackbone Model=Qwen3-30B-A3B2026.010.5170.512