# WMT26 leaderboard

Multilingual benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multilingual-wmt26

WMT26 General Machine Translation (all languages). Every model the catalog carries a published WMT26 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multilingual |
| Measure | 0-100 judged translation quality, averaged across languages |
| Tasks | General-domain translation across 50+ languages (32 high-resource plus 18 additional) |
| Difficulty | Professional machine translation |
| Published by | [WMT26 General Machine Translation Task](https://www2.statmt.org/wmt26/translation-task.html) |

Machine-translation quality on the WMT26 general translation task, averaged across all evaluated languages and scored 0-100 by an LLM judge.

## WMT26 ranking

1 model with a published WMT26 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | 0-100 judged translation quality, averaged across languages | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [North Small Translate](https://modelscale.dev/models/north-small-translate-1-0) | Cohere | 83.6 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
