OPUS-MT Dashboard

Language pair: [eng-fra] all languages
Models: [all models] [OPUS-MT] [external] [compare]
Selected: Tatoeba-MT-models/fiu-bat/opus-2021-02-19
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	est-lav	flores101-devtest	show	18.3
1	est-lav	ntrex128	show	12.9
2	est-lit	flores101-devtest	show	15.7
3	est-lit	flores200-devtest	show	15.7
4	est-lit	ntrex128	show	11.9
5	est-ltg	flores200-devtest	show	1.5
6	fin-lav	flores101-devtest	show	13.4
7	fin-lav	ntrex128	show	9.3
8	fin-lit	flores101-devtest	show	14.1
9	fin-lit	flores200-devtest	show	14.1
10	fin-lit	ntrex128	show	9.2
11	fin-ltg	flores200-devtest	show	1.1
			average	11.433