Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Machine Translation on Ru-En document-level
Loading...
84.59
d-COMET
Ours
80.9292
81.8796
82.83
83.7804
Apr 8, 2025
d-COMET
Updated 4d ago
Evaluation Results
Method
Method
Links
d-COMET
Ours
Base Model=Mistral-Nem...
2025.04
84.59
Ours (-QA)
Base Model=Mistral-Nem...
2025.04
83.89
SentRefine (sent)
Base Model=Mistral-Nem...
2025.04
83.87
Sent2Sent (tuned)
Base Model=Mistral-Nem...
2025.04
83.33
Sent2Sent
Base Model=Mistral-Nem...
2025.04
82.86
Ours
Base Model=LLaMA-3-8B-...
2025.04
82.75
DocRefine (doc)
Base Model=LLaMA-3-8B-...
2025.04
82.73
SentRefine (sent)
Base Model=LLaMA-3-8B-...
2025.04
82.64
Ours (-QA)
Base Model=LLaMA-3-8B-...
2025.04
82.63
Doc2Doc
Base Model=Mistral-Nem...
2025.04
82.6
Doc2Doc (tuned)
Base Model=Mistral-Nem...
2025.04
82.6
DocRefine (sent)
Base Model=Mistral-Nem...
2025.04
82.34
Sent2Sent (tuned)
Base Model=LLaMA-3-8B-...
2025.04
81.98
DocRefine (doc)
Base Model=Mistral-Nem...
2025.04
81.65
Sent2Sent
Base Model=LLaMA-3-8B-...
2025.04
81.63
Doc2Doc (tuned)
Base Model=LLaMA-3-8B-...
2025.04
81.25
DocRefine (sent)
Base Model=LLaMA-3-8B-...
2025.04
81.16
Doc2Doc
Base Model=LLaMA-3-8B-...
2025.04
81.07
Feedback
Search any
task
Search any
task