Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Idiomatic Translation on Mixed Dataset en-ta
Loading...
1.87
LLM-eval Score
IdiomCE
1.0068
1.2309
1.455
1.6791
May 28, 2025
LLM-eval Score
COMET Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-eval Score
COMET Score
IdiomCE
Model=GPT-4o
2025.05
1.87
0.67
Direct
Model=GPT-4o
2025.05
1.741
0.72
IdiomCE
Model=Gemma2-9b-it
2025.05
1.63
0.67
Direct
Model=Gemma2-9b-it
2025.05
1.56
0.71
IdiomCE
Model=LLama-3.1-8B
2025.05
1.25
0.57
Direct
Model=Indictrans2
2025.05
1.243
0.769
Direct
Model=NLLB-200
2025.05
1.18
0.691
Direct
Model=LLama-3.1-8B
2025.05
1.16
0.62
IdiomCE
Model=LLama-3.2-3B
2025.05
1.105
0.51
Direct
Model=LLama-3.2-3B
2025.05
1.04
0.52
Feedback
Search any
task
Search any
task
