WMT 2023 Discourse-Level Literary Translation
Version 2023
Models translate chapters of Chinese web novels into English. Professional translators mark errors and rank systems within each submission group.
The organizers publish the Chinese test chapters. They require institutional registration for the full corpus.
- Made by
- Tencent AI Lab and China Literature
- Released
- April 2023
- Kind
- Translation
- Level
- Expert
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Languages and literature
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- A host
- Occupations
- Arts, design, entertainment, sports and media
- Strongest model tested
- GPT-4 Jun 2023 #186 on the capability index
- Last model added
- June 2023
- Scores refreshed
- November 20th, 2026
DLUT tops the leaderboard with 63.4 GPT-4 leads with 54.8
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-4, at 54.8. This view shows only models we track, each at its best.
- 1 DLUT Primary (unconstrained) 63.4
- 2 GPT-4 Jun 2023, Baselines 54.8
- 3 HW-TSC Primary (unconstrained) 53.0
- 4 MAKE-NMT-VIZ Primary (constrained) 42.4
- 5 NTU Primary (unconstrained) 31.7
- 6 MaxLab Primary (constrained) 28.6
- 7 Llama-MT Baselines 28.4
- 8 Google Baselines 22.7
- 9 TJUNLP Primary (constrained) 18.3
- 10 HITer-WMT Primary (unconstrained) 5.56
Source: The WMT 2023 Discourse-Level Literary Translation paper
Source: The WMT 2023 Discourse-Level Literary Translation paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DLUT | 63.4 | Primary (unconstrained) | Official leaderboard | |
| 2 | GPT-4 Jun 2023 | 54.8 | Baselines | Jun 2023 | Official leaderboard |
| 3 | HW-TSC | 53.0 | Primary (unconstrained) | Official leaderboard | |
| 4 | MAKE-NMT-VIZ | 42.4 | Primary (constrained) | Official leaderboard | |
| 5 | NTU | 31.7 | Primary (unconstrained) | Official leaderboard | |
| 6 | MaxLab | 28.6 | Primary (constrained) | Official leaderboard | |
| 7 | Llama-MT | 28.4 | Baselines | Official leaderboard | |
| 8 | 22.7 | Baselines | Official leaderboard | ||
| 9 | TJUNLP | 18.3 | Primary (constrained) | Official leaderboard | |
| 10 | HITer-WMT | 5.56 | Primary (unconstrained) | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Jun 2023 | 54.8 | Baselines | Jun 2023 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official WMT 2023 Discourse-Level Literary Translation leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
Versions
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (10 entries).
- Pass Models scored 1 model we track, plus 9 other entries on its leaderboard.
- Note Newest score The newest came 3 years ago, in June 2023, for GPT-4. That’s expected for a test replaced by WMT 2024 Discourse-Level Literary Translation.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-4 (#186).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 1 row for models we track and 9 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.