WMT26 General Machine Translation (all languages)

Machine-translation quality on the WMT26 general translation task, averaged across all evaluated languages and scored 0-100 by an LLM judge.

1 models

Higher is better.

Higher is better. Bar colour: blue proprietary, orange open weights, green other.

Metric: 0-100 judged translation quality, averaged across languages
Tasks: General-domain translation across 50+ languages (32 high-resource plus 18 additional)
Authors: WMT organizers (2026)
Source: WMT26 General Machine Translation Task ↗

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.