# Translation Quality Scoring

M-Prometheus is an open-source LLM evaluation model capable of natively supporting multilingual output assessment. Trained on 480,000 multilingual direct evaluation and pairwise comparison data with long-text feedback.

M-Prometheus is an open-source LLM evaluation model capable of natively supporting multilingual output evaluation. It was trained on 480,000 multilingual direct evaluation and paired comparison data points.

M-Prometheus is an open-source LLM evaluation model that natively supports multilingual output evaluation. It is trained on 480,000 multilingual direct evaluation and pairwise comparison data points with detailed feedback.

UniTE is a unified framework for translation quality evaluation, supporting multilingual translation assessment.

UniTE is a unified framework for evaluating translation quality, specifically optimized for English target translation tasks.