Translation Set1→en COMET22
Progress Over Time
Interactive timeline showing model performance evolution on Translation Set1→en COMET22
Translation Set1→en COMET22 Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Amazon | — | — | — | ||
| 2 | Amazon | — | — | — | ||
| 3 | Amazon | — | — | — |
What is Translation Set1→en COMET22?
COMET-22 is a neural machine translation evaluation metric that uses an ensemble of two models: a COMET estimator trained with Direct Assessments and a multitask model that predicts sentence-level scores and word-level OK/BAD tags. It provides improved correlations with human judgments and increased robustness to critical errors compared to previous metrics.
Translation Set1→en COMET22 is a text benchmark evaluating models on language tasks. LLM Stats tracks 3 models on this benchmark, scored on a 0–1 scale. The current average is 0.9, with the leader at 0.9.
Compare leaders on the best AI for language leaderboards.
Current leaders
Nova Pro from Amazon currently leads the Translation Set1→en COMET22 leaderboard with a score of 0.890 across 3 evaluated AI models.
FAQ
Common questions about the Translation Set1→en COMET22 benchmark and leaderboard.