List your company

Translation Preference Prediction on WMT ZH -> EN

60.7Pairwise AccuracyDistribution-Calibrated Aggregation
50.8253.38555.9558.515Dec 2, 2025

Evaluation results

MethodLinks
Distribution-Calibrated Aggregationn=12, Judge LLM=gemini-2.5-flash2025.1260.7
USCn=12, Judge LLM=gemini-2.5-flash2025.1259
Distribution-Calibrated Aggregationn=4, Judge LLM=gemini-2.5-flash2025.1258.3
USCn=4, Judge LLM=gemini-2.5-flash2025.1256.1
GSCn=12, Judge LLM=gemini-2.5-flash2025.1255
CI-SCn=12, Judge LLM=gemini-2.5-flash2025.1254.5
SCn=12, Judge LLM=gemini-2.5-flash2025.1253.9
CI-SCn=4, Judge LLM=gemini-2.5-flash2025.1253
Soft-SCn=12, Judge LLM=gemini-2.5-flash2025.1252.9
Soft-SCn=4, Judge LLM=gemini-2.5-flash2025.1252.8
SCn=4, Judge LLM=gemini-2.5-flash2025.1251.5
GSCn=4, Judge LLM=gemini-2.5-flash2025.1251.2