OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/kor-fin/opus-2020-06-17
Benchmark: all benchmarks [download]
Evaluation metric: bleu [spbleu][chrf][chrf++][comet]
Chart Type: [barchart] [heatmap]

orange = OPUS-MT, blue = Tatoeba-MT models, red = HPLT-MT models
green = student models, grey = external models, purple = user-contributed
render chart with [gd] [plotly]

Model Scores (selected model)

ID	Language	Benchmark	Output	bleu
0	kor-fin	flores101-devtest	show	8.6
1	kor-fin	flores200-devtest	show	8.6
2	kor-fin	ntrex128	show	6.5
3	kor-fin	tatoeba-test-v2020-07-28	show	26
4	kor-fin	tatoeba-test-v2021-03-30	show	25.9
5	kor-fin	tatoeba-test-v2021-08-07	show	26.3
6	kor_Hang-fin	tatoeba-test-v2020-07-28	show	24.9
7	kor_Hang-fin	tatoeba-test-v2021-03-30	show	24.8
8	kor_Hang-fin	tatoeba-test-v2021-08-07	show	25
			average	19.622