Model card
DeepL.
DeepL SEproprietaryTransformer (NMT)
DeepL translation system. Evaluated as ONLINE-W in WMT23.
§ 01 · Benchmarks
Every benchmark DeepL has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | WMT'23 | Natural Language Processing · Machine Translation | comet | 83.5% | #3 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where DeepL actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.