Translation en→Set1 COMET22

language official site →

COMET-22 is an ensemble machine translation evaluation metric combining a COMET estimator model trained with Direct Assessments and a multitask model that predicts sentence-level scores and word-level OK/BAD tags. It demonstrates improved correlations compared to state-of-the-art metrics and increased robustness to critical errors.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: language. Language: en. Verified by llm-stats: no.

Leaderboard

  1. Nova Pro self-reported llm-stats
    89.1%
  2. Nova Lite self-reported llm-stats
    88.8%
  3. Nova Micro self-reported llm-stats
    88.5%