CLEF JOKER 2023 Task 3: Pun Translation
Version 2023
Models translate English puns into French or Spanish. Judges count translations that retain both the original meaning and wordplay. Organizers rank each language separately.
Nine teams submitted 47 runs. The organizers report Croland’s GPT-3 results in both languages. The Spanish judges assessed translations of 544 distinct English puns.
- Made by
- CLEF JOKER organizers
- Released
- September 2022
- Kind
- Translation
- Level
- University
- Scored
- Graded by people
- Answers
- Open-ended
- Measures
- Capability
- Subject
- Languages and literature
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- A host
- Scores refreshed
- November 20th, 2026
Google Translate tops the leaderboard with 81.5 T5-Large leads with 10.0
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline averages the French and Spanish counts of translations that preserve meaning and wordplay. 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 T5-Large, at 10.0. This view shows only models we track, each at its best.
- 1 Google Translate Smroltra 81.5
- 2 SimpleT5 Smroltra 79.5
- 3 Opus-MT Smroltra: EasyNMT 74.5
- 4 j2-grande TheLangVerse: Fine-tuned 68.5
- 5 T5-Large LJGG: No label 10.0
- 6 M2M_100 ThePunDetectives 4.50
- 7 mT5-base LJGG: With label 3.00
- 8 GPT-3 Croland 1.50
- 9 BLOOM Smroltra 1.00
Source: The CLEF JOKER 2023 Task 3: Pun Translation paper
Source: The CLEF JOKER 2023 Task 3: Pun Translation paper
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Google Translate | 81.5 | Smroltra | Smroltra | Official leaderboard | |
| 2 | SimpleT5 | 79.5 | Smroltra | Smroltra | Official leaderboard | |
| 3 | Opus-MT | 74.5 | Smroltra: EasyNMT | Smroltra | Official leaderboard | |
| 4 | j2-grande | 68.5 | TheLangVerse: Fine-tuned | TheLangVerse | Official leaderboard | |
| 5 | T5-Large | 10.0 | LJGG: No label | LJGG | Official leaderboard | |
| 6 | M2M_100 | 4.50 | ThePunDetectives | ThePunDetectives | Official leaderboard | |
| 7 | mT5-base | 3.00 | LJGG: With label | LJGG | Official leaderboard | |
| 8 | GPT-3 | 1.50 | Croland | Croland | Official leaderboard | |
| 9 | BLOOM | 1.00 | Smroltra | Smroltra | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | T5-Large | 10.0 | LJGG: No label | LJGG | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No dated values yet.
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
7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 1 model we track, plus 8 other entries on its leaderboard.
- Note Newest score No scores yet.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on ceur-ws.org: 2 rows for models we track and 8 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.