Benchmark

WMT23

language text 多语言

The Eighth Conference on Machine Translation (WMT23) benchmark evaluating machine translation systems across 8 language pairs (14 translation directions) including general, biomedical, literary, and low-resource language translation tasks. Features specialized shared tasks for quality estimation, metrics evaluation, sign language translation, and discourse-level literary translation with professional human assessment.

语言EN
满分1
参评模型4

模型排名

名次 模型 机构 分数 来源
1 Gemini 1.5 Pro Google 75.1 来源 ↗
2 Gemini 1.5 Flash Google 74.1 来源 ↗
3 Gemini 1.5 Flash 8B Google 72.6 来源 ↗
4 Gemini 1.0 Pro Google 71.7 来源 ↗