CLEF JOKER 2026 Task 4: Humour Generation
Models write a joke using a target word in two specified senses. Three language models compare pairs of jokes for each language ranking.
The organizers rank 365 language-specific runs with Bradley-Terry ratings. The test contains 457 writing prompts across English, Spanish, and French.
- Made by
- CLEF JOKER organizers
- Released
- October 2025
- Kind
- Creative writing
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Measures
- Preference
- Subject
- Languages and literature
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Kimi K2.6 leads with 1,389 among models released by April 2026 Kimi K2.6 leads with 1,389 among models released by April 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
Bars start at 400.
- 1 Kimi K2.6 1,389
- 2
Gemini 3 Flash Pun prompt 1,252
- 3 HumorGen-JOKER-14B 1,251
- 4 HumorGen-JOKER-32B 1,250
- 5
Qwen3-4B Pun prompt 1,075
- 6 Gemma-2-9B-it Pun prompt 1,014
- 7 Mistral-7B (instruction-tuned, version unspecified) Pun prompt 970
- 8 Llama-3.1-8B-Instruct Pun prompt 957
- 9
Mistral-7B-Instruct-v0.2 929
- 10 flan-t5-large 500
- 11 flan-t5-base 425
Source: Official CLEF JOKER 2026 Task 4: Humour Generation leaderboard
Bars start at 900.
- 1 Kimi K2.6 1,389
- 2
Gemini 3 Flash Pun prompt 1,252
- 3
Qwen3-4B Pun prompt 1,075
- 4
Mistral-7B-Instruct-v0.2 929
Source: Official CLEF JOKER 2026 Task 4: Humour Generation leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Kimi K2.6 | 1,389 | Cognitive Synergy Framework | SaLT | Apr 2026 | Official leaderboard |
| 2 | | 1,252 | Pun prompt | UBO | Dec 2025 | Official leaderboard |
| 3 | HumorGen-JOKER-14B | 1,251 | SaLT | Official leaderboard | ||
| 4 | HumorGen-JOKER-32B | 1,250 | SaLT | Official leaderboard | ||
| 5 | | 1,075 | Pun prompt | UBO | Apr 2025 | Official leaderboard |
| 6 | Gemma-2-9B-it | 1,014 | Pun prompt | UBO | Official leaderboard | |
| 7 | Mistral-7B (instruction-tuned, version unspecified) | 970 | Pun prompt | UBO | Official leaderboard | |
| 8 | Llama-3.1-8B-Instruct | 957 | Pun prompt | UBO | Official leaderboard | |
| 9 | | 929 | Humor detection and pun reranking | UAms | Dec 2023 | Official leaderboard |
| 10 | flan-t5-large | 500 | Humor detection and pun reranking | UAms | Official leaderboard | |
| 11 | flan-t5-base | 425 | Humor detection and pun reranking | UAms | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Kimi K2.6 | 1,389 | Cognitive Synergy Framework | SaLT | Apr 2026 | Official leaderboard |
| 2 | | 1,252 | Pun prompt | UBO | Dec 2025 | Official leaderboard |
| 3 | | 1,075 | Pun prompt | UBO | Apr 2025 | Official leaderboard |
| 4 | | 929 | Humor detection and pun reranking | UAms | Dec 2023 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: English, Spanish and French. Each ranks models on one part of the test. Kimi K2.6 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
English
4 models we track have a score here.
- 1 Kimi K2.6 1,257
- 2
Gemini 3 Flash 1,125
- 3
Qwen3-4B 995
- 4
Mistral-7B-Instruct-v0.2 922
Spanish
4 models we track have a score here.
- 1 Kimi K2.6 1,515
- 2
Gemini 3 Flash 1,351
- 3
Qwen3-4B 1,100
- 4
Mistral-7B-Instruct-v0.2 903
French
4 models we track have a score here.
- 1 Kimi K2.6 1,395
- 2
Gemini 3 Flash 1,279
- 3
Qwen3-4B 1,130
- 4
Mistral-7B-Instruct-v0.2 961
3 models have held number one on the official leaderboard since its release in October 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official CLEF JOKER 2026 Task 4: Humour Generation 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 CLEF JOKER 2026 Task 4: Humour Generation 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.
More in Writing and taste
- Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
- WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
- Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing.
MiniMax-Text-01 81.3%
- DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate.
DeepSeek-V4-Pro 62.6%
- Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
- Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right.
Muse Spark 0.21
Data audit
7 of 9 checks pass, 2 warnings. 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 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 4 models we track, plus 7 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Kimi K2.6.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Flash (#60).
- Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on joker-project.com: 5 rows for models we track and 7 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.