Preliminary Ranking of WMT25 General Machine Translation Systems

TL;DR

This paper provides preliminary automatic rankings of WMT25 machine translation systems, highlighting potential biases and emphasizing that human evaluation will ultimately determine the official rankings.

Contribution

It offers early automatic evaluation results for WMT25 MT systems, aiding participants before official human-based rankings are released.

Findings

Preliminary rankings based on automatic metrics.

Bias towards re-ranking techniques in automatic evaluation.

Official rankings will rely on human evaluation.

Abstract

We present the preliminary rankings of machine translation (MT) systems submitted to the WMT25 General Machine Translation Shared Task, as determined by automatic evaluation metrics. Because these rankings are derived from automatic evaluation, they may exhibit a bias toward systems that employ re-ranking techniques, such as Quality Estimation or Minimum Bayes Risk decoding. The official WMT25 ranking will be based on human evaluation, which is more reliable and will supersede these results. The official WMT25 ranking will be based on human evaluation, which is more reliable and will supersede these results. The purpose of releasing these findings now is to assist task participants with their system description papers; not to provide final findings.