OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/bat-fiu/opus-2021-02-18
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	lav-est	flores101-devtest	show	15.2
1	lav-est	ntrex128	show	13.6
2	lav-fin	flores101-devtest	show	11.5
3	lav-fin	ntrex128	show	8.9
4	lit-est	flores101-devtest	show	14.1
5	lit-est	flores200-devtest	show	14.3
6	lit-est	ntrex128	show	12.8
7	lit-fin	flores101-devtest	show	11.7
8	lit-fin	flores200-devtest	show	11.9
9	lit-fin	ntrex128	show	9.1
10	ltg-est	flores200-devtest	show	4.2
11	ltg-fin	flores200-devtest	show	2.7
			average	10.833